wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-24 13:20:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support SqueezeLLM (#1326)

Browse Source 
Co-authored-by: squeeze-ai-lab <squeezeailab.bair@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
chooper1
2023-10-21 23:14:59 -07:00
committed by GitHub
co-authored by squeeze-ai-lab Woosuk Kwon
parent bf31d3606a
commit 1f24755bf8
16 changed files with 378 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
csrc/quantization.cpp
+8 -4
View File
@@ -7,9 +7,13 @@ torch::Tensor awq_gemm(
torch::Tensor _zeros,
int split_k_iters);
void squeezellm_gemm(
torch::Tensor vec,
torch::Tensor mat,
torch::Tensor mul,
torch::Tensor lookup_table);
PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
m.def(
"awq_gemm",
&awq_gemm,
"Quantized GEMM for AWQ");
m.def("awq_gemm", &awq_gemm, "Quantized GEMM for AWQ");
m.def("squeezellm_gemm", &squeezellm_gemm, "Quantized GEMM for SqueezeLLM");
}