Index of sw-kernelinferencelibrary-public-generic-local/d8c2e4e646bd7e73ea79f06ae52b4ba13adddc64/batched_gemm-6492001-c97c649
Name Last modified Size
../
include/ 21-Aug-2025 12:36 -
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256_s6_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 111.17 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256_s6_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.12 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256u2_s6_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 114.55 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256u2_s6_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.63 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 108.27 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.88 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x4_16dp256b_splitK4_TN_transOut_schedP_bN_tma_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 122.11 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512u2_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 113.63 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512u2_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.02 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256_s6_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.88 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256_s6_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.82 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256u2_s6_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.13 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256u2_s6_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.20 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 108.74 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.36 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512u2_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 114.08 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512u2_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.49 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 113.83 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.55 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256u2_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 116.93 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256u2_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.05 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512_s3_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.38 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512_s3_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.73 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512u2_s3_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 115.60 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512u2_s3_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.11 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256_s6_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.54 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256_s6_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 91.41 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256u2_s6_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 113.93 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256u2_s6_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.05 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 107.67 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.30 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 88.71 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x4_16dp256b_splitK4_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 115.41 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x4_16dp256b_splitK4_TN_transOut_schedP_bN_tma_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 119.27 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.71 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.80 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 93.44 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 92.97 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x3_16dp256b_splitK3_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 119.12 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.16 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 78.77 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.48 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 80.30 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.91 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 78.64 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.35 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 80.18 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.55 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.70 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 103.88 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.12 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.30 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.58 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 103.75 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 82.99 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 67.38 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 57.22 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 70.81 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 61.03 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.45 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 79.38 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.67 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.77 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.33 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 79.26 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.55 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.65 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.73 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 82.45 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.95 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.84 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.60 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 82.20 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.82 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.71 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 67.63 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 57.53 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512u2_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.43 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512u2_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 88.27 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.43 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.06 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.80 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.47 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.30 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 82.94 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.55 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.34 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.83 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 85.88 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 111.09 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.41 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.58 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 85.75 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.96 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.28 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 69.12 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.05 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512u2_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.94 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512u2_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.78 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 80.02 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 80.84 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 79.89 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 80.71 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.72 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.03 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.49 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.85 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.59 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.91 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.37 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.73 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.96 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 83.78 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.84 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 83.66 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.93 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.10 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.72 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.92 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.68 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.98 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.47 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.79 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 66.74 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 56.59 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 56.07 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 70.30 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 60.53 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 59.89 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 69.67 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 71.70 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 57.66 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 58.31 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256u2_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 71.89 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256u2_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 74.05 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256u2_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.76 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x16x256u2_s3_et128x16_m128x16x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 60.53 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 70.30 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 75.71 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 58.29 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 61.56 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256u2_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 72.52 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256u2_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 77.93 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256u2_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 60.38 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x32x256u2_s3_et128x32_m128x32x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 63.78 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 71.55 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.31 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.54 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 68.06 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256u2_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 73.77 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256u2_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 85.84 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256u2_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 61.63 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x64x256u2_s3_et128x64_m128x64x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 70.16 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 69.17 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 71.48 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 57.16 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.47 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256u2_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 71.64 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256u2_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 73.82 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256u2_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.38 KB
Bmm_Bfloat16_MxE2m1Bfloat16_castBfloat16_patch_Fp32_t128x8x256u2_s3_et128x8_m128x8x16_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 61.56 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.96 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 77.27 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256u2_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.16 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256u2_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 80.73 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.05 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 78.37 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256u2_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.23 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256u2_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.82 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.00 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.33 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.20 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.78 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.34 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 76.65 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.47 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 79.98 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.28 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 73.96 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.77 KB
Bmm_Bfloat16_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 78.72 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 116.50 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.59 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.01 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.95 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.67 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.73 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256u2_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.05 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x16x256u2_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.35 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.00 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 91.15 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.38 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 93.52 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256u2_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.16 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256u2_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.30 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256u2_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.54 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x32x256u2_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.91 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 118.57 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.70 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 119.08 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.05 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 122.73 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.84 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 123.11 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.34 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 116.40 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.51 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 125.44 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.12 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.77 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 92.41 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 126.80 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.20 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 118.84 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 93.22 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 127.87 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.14 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.44 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.66 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 129.47 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.39 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.80 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.55 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 130.96 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.36 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 122.88 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.50 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 131.77 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 103.30 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 105.96 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 88.77 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 114.10 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 94.15 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.38 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 93.91 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 118.66 KB
Bmm_Bfloat16_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.29 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.66 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.24 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512_s4_et128x16_m128x16x64_cga1x1x4_16dp256b_splitK4_TN_transOut_schedP_bN_tma_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 125.27 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512u2_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.46 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512u2_s4_et128x16_m128x16x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.24 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.29 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 107.81 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512u2_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 125.32 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512u2_s4_et128x32_m128x32x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 111.96 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 137.20 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.48 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256u2_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 140.46 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256u2_s6_et128x64_m128x64x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 124.98 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 118.62 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 89.63 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.18 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x4_16dp256b_splitK4_TN_transOut_schedP_bN_tma_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.11 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_geGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 122.63 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedP_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 122.38 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 93.77 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.18 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.87 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.65 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.12 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.77 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.74 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.40 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 103.87 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 84.52 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 107.48 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.57 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 108.51 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.57 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 107.23 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.45 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 108.25 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_s6_et64x16_m64x16x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.45 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x512_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 58.60 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x512u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 62.39 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 105.04 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.63 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.95 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 88.42 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.91 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.51 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.83 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 88.30 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 109.47 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.68 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 111.27 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 91.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 109.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.43 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 111.13 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_s4_et64x32_m64x32x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 91.22 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x512_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 62.16 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x512u2_s2_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 79.88 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 115.91 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.93 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 119.63 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.10 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 115.66 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.68 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 119.38 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.98 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.52 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.85 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 124.00 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.27 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.73 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 123.88 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_s4_et64x64_m64x64x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.90 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x512_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 70.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x512u2_s2_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.74 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.87 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 81.89 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.73 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.15 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.05 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.72 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.66 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.90 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 86.92 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.59 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 87.54 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 84.96 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 85.69 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 84.84 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 85.55 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.27 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.90 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.84 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.50 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 89.77 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.71 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_s8_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_clmp_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.37 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 55.96 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 59.53 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 59.66 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_tokSfB_schedS_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 63.32 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.27 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 79.80 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256u2_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.84 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x16x256u2_s5_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.23 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 96.39 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 80.09 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256u2_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.96 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x32x256u2_s5_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.54 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 105.59 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 88.18 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 109.19 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 91.49 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.34 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 80.11 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.83 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 83.30 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 90.91 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 76.48 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 95.04 KB
Bmm_E4m3_MxE2m1E4m3_castMxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 81.23 KB
Bmm_Fp16_E2m1E2m1_Fp32_t128x8x512_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 88.59 KB
Bmm_Fp16_E2m1E2m1_Fp32_t128x8x512u2_s4_et128x8_m128x8x64_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 92.72 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 79.90 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 80.71 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 79.77 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 80.59 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.84 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_BN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 83.66 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 82.71 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_s3_et64x8_m64x8x32_cga1x1x1_16dp256b_TN_transOut_noShflA_dsFp8_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 83.53 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 55.95 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_bN_clmp_sm100a.cubin 21-Aug-2025 12:36 59.64 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 123.27 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.61 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 123.92 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 99.91 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 127.17 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256u2_s3_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.48 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256u2_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 127.95 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x16x256u2_s4_et128x16_m128x16x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.03 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 128.45 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.96 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 129.11 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.12 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256u2_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 132.70 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256u2_s3_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 108.96 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256u2_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 133.36 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x32x256u2_s4_et128x32_m128x32x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.00 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 140.84 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 116.20 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 141.63 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.97 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 145.77 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256u2_s3_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.34 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 146.43 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x64x256u2_s4_et128x64_m128x64x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 121.99 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 124.86 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 98.95 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 132.77 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 103.66 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 126.08 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 100.16 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 133.99 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 105.32 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 127.02 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.13 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 134.93 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.29 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 128.98 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.85 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 136.91 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s4_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 107.66 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 130.20 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 104.16 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 138.01 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s5_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 109.32 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 131.14 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 105.12 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 138.95 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x256u2_s6_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 110.29 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 113.04 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 97.01 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 120.99 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 101.16 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 117.65 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x1_16dp256b_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 102.44 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedP_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 125.52 KB
Bmm_MxE4m3_MxE2m1MxE4m3_Fp32_t128x8x512u2_s3_et128x8_m128x8x32_cga1x1x2_16dp256b_splitK2_TN_transOut_schedS_biasM_bN_ldgsts_clmp_swiGlu_dynBatch_sm100a.cubin 21-Aug-2025 12:36 106.55 KB
LICENSE 21-Aug-2025 12:36 11.09 KB
target_path.txt 21-Aug-2025 12:36 29 bytes
Artifactory/7.55.14 Server at edge.urm.nvidia.com Port 80