fix(quantization): Fix AWQ dequantize on Intel XPU and refactor AutoAWQ config (#42727)

Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: AlexHuang <jihuihuang@tencent.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
AlexHuang
2026-06-18 20:12:28 +08:00
committed by GitHub
co-authored by Claude Kunshang Ji mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 351c72d6e5
commit 8d4f54966c
20 changed files with 580 additions and 429 deletions
+2 -2
View File
@@ -49,7 +49,7 @@ To run an AWQ model with vLLM, you can use [TheBloke/Llama-2-7b-Chat-AWQ](https:
```bash
python examples/deployment/llm_engine_example.py \
--model TheBloke/Llama-2-7b-Chat-AWQ \
--quantization awq
--quantization auto_awq
```
AWQ models are also supported directly through the LLM entrypoint:
@@ -70,7 +70,7 @@ AWQ models are also supported directly through the LLM entrypoint:
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
# Create an LLM.
llm = LLM(model="TheBloke/Llama-2-7b-Chat-AWQ", quantization="AWQ")
llm = LLM(model="TheBloke/Llama-2-7b-Chat-AWQ", quantization="auto_awq")
# Generate texts from the prompts. The output is a list of RequestOutput objects
# that contain the prompt, generated text, and other information.
outputs = llm.generate(prompts, sampling_params)