Integrate Marlin Kernels for Int4 GPTQ inference (#2497)
Co-authored-by: Robert Shaw <114415538+rib-2@users.noreply.github.com> Co-authored-by: alexm <alexm@neuralmagic.com>
This commit is contained in:
co-authored by
Robert Shaw
alexm
parent
90fbf12540
commit
c0c2335ce0
@@ -342,6 +342,8 @@ vllm_extension_sources = [
|
||||
|
||||
if _is_cuda():
|
||||
vllm_extension_sources.append("csrc/quantization/awq/gemm_kernels.cu")
|
||||
vllm_extension_sources.append(
|
||||
"csrc/quantization/marlin/marlin_cuda_kernel.cu")
|
||||
vllm_extension_sources.append("csrc/custom_all_reduce.cu")
|
||||
|
||||
# Add MoE kernels.
|
||||
|
||||
Reference in New Issue
Block a user