[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:
co-authored by
mgoin
Divakar Verma
Tyler Michael Smith
parent
ee5f34b1c2
commit
86e9c8df29
@@ -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")
|
||||
|
||||
Reference in New Issue
Block a user