Yuan Luoandluoyuan.luo 432f2053dd [sgl-kernel] 1/N Refactor sglang cutlass 3x - gemm fp8 blockwise sm90 (#8913) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2025-08-14 10:55:54 -07:00

..

gptq

[2/n]decouple quantization implementation from vLLM dependency (#8112)

2025-08-14 03:19:03 -07:00

marlin

[2/n]decouple quantization implementation from vLLM dependency (#8112)

2025-08-14 03:19:03 -07:00

awq_kernel.cu

…

bmm_fp8.cu

…

dsv3_fused_a_gemm.cu

…

dsv3_router_gemm_bf16_out.cu

…

dsv3_router_gemm_entry.cu

…

dsv3_router_gemm_float_out.cu

…

fp8_blockwise_gemm_kernel.cu

[sgl-kernel] 1/N Refactor sglang cutlass 3x - gemm fp8 blockwise sm90 (#8913)

2025-08-14 10:55:54 -07:00

fp8_gemm_kernel.cu

…

int8_gemm_kernel.cu

…

math.hpp

…

nvfp4_expert_quant.cu

…

nvfp4_quant_entry.cu

…

nvfp4_quant_kernels.cu

…

nvfp4_scaled_mm_entry.cu

…

nvfp4_scaled_mm_kernels.cu

…

per_tensor_quant_fp8.cu

…

per_token_group_quant_8bit.cu

…

per_token_quant_fp8.cu

[sgl-kernel] avoid per_token_quant_fp8.cu hardcode sm_count (#8738)

2025-08-04 12:55:57 +08:00

qserve_w4a8_per_chn_gemm.cu

…

qserve_w4a8_per_group_gemm.cu

…