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

[Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Li, Jiang
2026-01-07 03:10:18 +08:00
committed by GitHub
parent c07163663d
commit 8becf146bd
9 changed files with 171 additions and 332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/quantization/test_cpu_wna16.py
View File

@@ -10,6 +10,7 @@ if not current_platform.is_cpu():
MODELS = [
"TheBloke/TinyLlama-1.1B-Chat-v1.0-AWQ",
"TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ", # with g_idx
"Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4", # without g_idx
]
DTYPE = ["bfloat16"]