[Kernel] Marlin Expansion: Support AutoGPTQ Models with Marlin (#3922)
Co-authored-by: alexm <alexm@neuralmagic.com> Co-authored-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
co-authored by
alexm
mgoin
parent
df29793dc7
commit
73c8d677e5
@@ -177,6 +177,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
|
||||
"csrc/quantization/aqlm/gemm_kernels.cu"
|
||||
"csrc/quantization/awq/gemm_kernels.cu"
|
||||
"csrc/quantization/marlin/marlin_cuda_kernel.cu"
|
||||
"csrc/quantization/gptq_marlin/gptq_marlin.cu"
|
||||
"csrc/quantization/gptq_marlin/gptq_marlin_repack.cu"
|
||||
"csrc/custom_all_reduce.cu")
|
||||
endif()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user