Skip to content

GitLab

"git@developer.sourcefind.cn:renzhc/diffusers_dcu.git" did not exist on "214372aa99edae6cb355e20df23b9150bb3b322d"
Unverified Commit 2acd76f3 authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

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

parent b81a6a6b
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
setup.py
View file @ 2acd76f3
...@@ -219,13 +219,13 @@ vllm_extension_sources = [ ...@@ -219,13 +219,13 @@ vllm_extension_sources = [
"csrc/activation_kernels.cu", "csrc/activation_kernels.cu",
"csrc/layernorm_kernels.cu", "csrc/layernorm_kernels.cu",
"csrc/quantization/squeezellm/quant_cuda_kernel.cu", "csrc/quantization/squeezellm/quant_cuda_kernel.cu",
"csrc/quantization/gptq/q_gemm.cu",
"csrc/cuda_utils_kernels.cu", "csrc/cuda_utils_kernels.cu",
"csrc/pybind.cpp", "csrc/pybind.cpp",
] ]
if _is_cuda(): if _is_cuda():
vllm_extension_sources.append("csrc/quantization/awq/gemm_kernels.cu") vllm_extension_sources.append("csrc/quantization/awq/gemm_kernels.cu")
vllm_extension_sources.append("csrc/quantization/gptq/q_gemm.cu")
vllm_extension = CUDAExtension( vllm_extension = CUDAExtension(
name="vllm._C", name="vllm._C",
......
vllm/config.py
View file @ 2acd76f3
...@@ -143,7 +143,7 @@ class ModelConfig: ...@@ -143,7 +143,7 @@ class ModelConfig:
def _verify_quantization(self) -> None: def _verify_quantization(self) -> None:
supported_quantization = ["awq", "gptq", "squeezellm"] supported_quantization = ["awq", "gptq", "squeezellm"]
rocm_not_supported_quantization = ["awq"] rocm_not_supported_quantization = ["awq", "gptq"]
if self.quantization is not None: if self.quantization is not None:
self.quantization = self.quantization.lower() self.quantization = self.quantization.lower()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment