biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm] Temporarily remove GPTQ ROCm support (#2138)

Browse Source
This commit is contained in:
Woosuk Kwon
2023-12-15 17:13:58 -08:00
committed by GitHub
parent b81a6a6bb3
commit 2acd76f346
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@@ -219,13 +219,13 @@ vllm_extension_sources = [
"csrc/activation_kernels.cu",
"csrc/layernorm_kernels.cu",
"csrc/quantization/squeezellm/quant_cuda_kernel.cu",
"csrc/quantization/gptq/q_gemm.cu",
"csrc/cuda_utils_kernels.cu",
"csrc/pybind.cpp",
]
if _is_cuda():
vllm_extension_sources.append("csrc/quantization/awq/gemm_kernels.cu")
vllm_extension_sources.append("csrc/quantization/gptq/q_gemm.cu")
vllm_extension = CUDAExtension(
name="vllm._C",