Index of sw-kernelinferencelibrary-public-generic-local/991e7438224199de85ef08a2730ce18c12b4e0aa/batched_gemm-c603ed2-2dc78d9
Name Last modified Size
../
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256_et128x16_m128x16x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 110.14 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256_et128x16_m128x16x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 91.15 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 113.66 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x256u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 94.66 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 107.23 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.12 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 112.45 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x16x512u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.26 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256_et128x32_m128x32x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 116.66 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256_et128x32_m128x32x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 91.70 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 120.05 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x256u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 95.33 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 107.70 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.58 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 112.89 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x32x512u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.72 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 112.68 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 93.68 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 116.03 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x256u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.06 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512_et128x64_m128x64x64_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.21 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512_et128x64_m128x64x64_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 88.98 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 114.41 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x64x512u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 93.12 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256_et128x8_m128x8x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.52 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256_et128x8_m128x8x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.44 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 113.02 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x256u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 94.07 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.62 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 85.52 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 85.06 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 111.93 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 89.66 KB
Bmm_Bfloat16_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 89.20 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.39 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 78.40 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.59 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 79.94 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.14 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 78.40 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.34 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 79.81 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.76 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 81.46 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.20 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 82.88 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.63 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 81.34 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.95 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 82.88 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 77.97 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 65.16 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512u2_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 81.40 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x16x512u2_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 68.98 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.48 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 77.38 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 101.70 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 79.77 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.22 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 77.25 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 101.45 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 79.64 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.97 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 80.44 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.07 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 82.83 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.71 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 80.31 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 105.95 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 82.70 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 77.93 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 60.34 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512u2_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 111.09 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x32x512u2_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 92.12 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.99 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 81.05 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.02 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 85.46 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.74 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 80.93 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 108.77 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 85.34 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.60 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.99 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 113.63 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 88.52 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.35 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.99 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 113.38 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 88.40 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 79.43 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 61.85 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512u2_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 112.51 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x64x512u2_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 93.63 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 79.77 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 80.59 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 79.65 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 80.47 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.85 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.91 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.64 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 84.73 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.73 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.79 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.52 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 84.60 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.59 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 83.41 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.47 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 83.29 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.42 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.73 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.09 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.55 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.17 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.61 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.84 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.42 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 77.44 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 64.66 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 64.02 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedP_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 80.86 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_dynBatch_sm100a.cubin 25-Jul-2025 11:13 68.35 KB
Bmm_Bfloat16_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 67.84 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 114.67 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.02 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.81 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x16x512u2_et128x16_m128x16x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.05 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 117.32 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.48 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 122.81 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x32x512u2_et128x32_m128x32x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.60 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 131.06 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 115.68 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 134.32 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x64x256u2_et128x64_m128x64x64_cga1x1x1_16dp256b_s6_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.31 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 115.89 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 93.58 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 85.98 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedP_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.77 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.48 KB
Bmm_E2m1_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 90.12 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.52 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.37 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.65 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 84.38 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 102.39 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.24 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.40 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 84.25 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.82 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.29 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 107.84 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.30 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.70 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.16 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 107.72 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x128u2_et64x16_m64x16x32_cga1x1x1_16dp256b_s6_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.17 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x512_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 60.14 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x16x512u2_et128x16_m128x16x32_cga1x1x1_16dp256b_s3_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 64.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.59 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 85.60 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.38 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.27 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 85.48 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 106.24 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.14 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 108.29 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 88.52 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 110.06 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.31 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 108.16 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 88.40 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 109.94 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x128u2_et64x32_m64x32x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.19 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x512_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 60.45 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x32x512u2_et128x32_m128x32x32_cga1x1x1_16dp256b_s2_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 83.97 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 115.40 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 95.05 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.14 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 98.10 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 115.27 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 94.92 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.98 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.85 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 122.95 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 101.15 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 119.09 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 97.84 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 122.70 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x128u2_et64x64_m64x64x32_cga1x1x1_16dp256b_s4_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 101.02 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x512_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 66.05 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x64x512u2_et128x64_m128x64x32_cga1x1x1_16dp256b_s2_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 89.56 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 81.77 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.49 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 81.65 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.37 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.47 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.90 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 100.05 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.38 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.22 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 86.77 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 99.92 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 87.26 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 84.59 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 85.31 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 84.47 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 85.31 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.65 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 89.50 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_BN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.34 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 103.40 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 89.50 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedP_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 104.21 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s8_TN_transOut_noShflA_dsFp8_schedS_bN_ldgsts_dynBatch_sm100a.cubin 25-Jul-2025 11:13 90.22 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 63.91 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 61.83 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 67.61 KB
Bmm_E4m3_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_tokSfB_schedS_bN_ldgsts_swiGlu_dynBatch_sm100a.cubin 25-Jul-2025 11:13 65.77 KB
Bmm_Fp16_E2m1E2m1_Fp32_t128x8x512_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 84.81 KB
Bmm_Fp16_E2m1E2m1_Fp32_t128x8x512u2_et128x8_m128x8x64_cga1x1x1_16dp256b_s4_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 88.95 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 79.52 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 80.34 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 79.40 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 80.22 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.59 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_BN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 83.41 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 82.47 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x128u2_et64x8_m64x8x32_cga1x1x1_16dp256b_s3_TN_transOut_noShflA_dsFp8_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 83.29 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x512_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 63.90 KB
Bmm_Fp16_E4m3E4m3_Fp32_t128x8x512u2_et128x8_m128x8x32_cga1x1x1_16dp256b_s3_TN_transOut_schedS_bN_sm100a.cubin 25-Jul-2025 11:13 67.59 KB
export.tgz 25-Jul-2025 11:13 9.61 MB
LICENSE 25-Jul-2025 11:13 11.09 KB
target_path.txt 25-Jul-2025 11:13 29 bytes
Artifactory/7.55.14 Server at edge.urm.nvidia.com Port 80