[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2024-09-23 13:46:26 -04:00
committed by GitHub
co-authored by mgoin Divakar Verma Tyler Michael Smith
parent ee5f34b1c2
commit 86e9c8df29
27 changed files with 1005 additions and 246 deletions
+1
View File
@@ -223,6 +223,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
"csrc/quantization/gguf/gguf_kernel.cu"
"csrc/quantization/fp8/fp8_marlin.cu"
"csrc/custom_all_reduce.cu"
"csrc/permute_cols.cu"
"csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu"
"csrc/quantization/cutlass_w8a8/scaled_mm_c2x.cu"
"csrc/quantization/cutlass_w8a8/scaled_mm_c3x.cu")