likesen-alibaba 4a0d19198b Fix bug of deepseek-v3 under DP+EP mode with large batchsize/seqlen (#6449)

2025-07-10 01:19:56 -07:00

..

awq_kernel.cu

Fix AWQ Dequant and Weight Loading of deepseek v2 (#6842)

2025-06-17 13:45:10 -07:00

bmm_fp8.cu

…

dsv3_fused_a_gemm.cu

Add dsv3 fused a gemm to sgl-kernel (#7630)

2025-06-29 02:52:24 -07:00

dsv3_router_gemm.cu

Add dsv3 router gemm kernel (#7627)

2025-06-29 23:31:55 -07:00

fp8_blockwise_gemm_kernel.cu

Upgrade CUTLASS 4.0 (#6336)

2025-05-15 17:42:23 -07:00

fp8_gemm_kernel.cu

…

int8_gemm_kernel.cu

…

nvfp4_expert_quant.cu

[1/2] Add Kernel support for Cutlass based Fused FP4 MoE (#6093)

2025-06-02 13:48:03 -07:00

nvfp4_quant_entry.cu

[1/2] Add Kernel support for Cutlass based Fused FP4 MoE (#6093)

2025-06-02 13:48:03 -07:00

nvfp4_quant_kernels.cu

…

nvfp4_scaled_mm_entry.cu

…

nvfp4_scaled_mm_kernels.cu

[Build] Fix cuda12.8 build error in nvfp4_scaled_mm_kernels.cu (#4953)

2025-03-31 12:00:34 -07:00

per_tensor_quant_fp8.cu

…

per_token_group_quant_8bit.cu

Fix bug of deepseek-v3 under DP+EP mode with large batchsize/seqlen (#6449)

2025-07-10 01:19:56 -07:00

per_token_quant_fp8.cu

Speed up per token and per tensor quant by 15% (#4639)

2025-03-22 00:37:57 -07:00

qserve_w4a8_per_chn_gemm.cu

[1/2] Support Qserve (#6457)

2025-05-21 19:48:59 -07:00

qserve_w4a8_per_group_gemm.cu

[1/2] Support Qserve (#6457)

2025-05-21 19:48:59 -07:00