wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-17 11:34:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add GPTQ support (#916)

Browse Source
This commit is contained in:
CHU Tianxiang
2023-12-15 03:04:22 -08:00
committed by GitHub
parent c06170cc8e
commit 0fbfc4b81b
35 changed files with 1782 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files
csrc/pybind.cpp
+2 -2
View File
@@ -52,8 +52,8 @@ PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
// Quantization ops
ops.def("awq_gemm", &awq_gemm, "Quantized GEMM for AWQ");
#endif
ops.def("gptq_gemm", &gptq_gemm, "Quantized GEMM for GPTQ");
ops.def("gptq_shuffle", &gptq_shuffle, "Post processing for GPTQ");
ops.def("squeezellm_gemm", &squeezellm_gemm, "Quantized GEMM for SqueezeLLM");
// Cache ops