Add GPTQ support (#916)

This commit is contained in:
CHU Tianxiang
2023-12-15 19:04:22 +08:00
committed by GitHub
parent c06170cc8e
commit 0fbfc4b81b
35 changed files with 1782 additions and 82 deletions

View File

@@ -219,6 +219,7 @@ 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",
]