liu 688350a3bb [bugfixed] fix the bug when run the inference of quantized ds-w8a8-mtp (#2134) ...

When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has
no attribute 'params_dtype''.

1. add wrapper of vocab_parallel_embedding, fixed the bugs when running
deepseek-w8a8-mtp

Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>

- vLLM version: v0.10.0
- vLLM main:
ad57f23f6a

---------

Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>

2025-08-04 15:16:42 +08:00

..

__init__.py

[Core] Cherry pick from 0.7.1 to keep the main code newest (#127)

2025-02-21 17:07:37 +08:00

func_wrapper.py

[bugfixed] fix the bug when run the inference of quantized ds-w8a8-mtp (#2134)

2025-08-04 15:16:42 +08:00

quant_config.py

[main][Feature] Support Qwen3 W4A8 quantization (#2060)

2025-07-30 14:57:14 +08:00

quantizer.py

[bugfixed] fix the bug when run the inference of quantized ds-w8a8-mtp (#2134)

2025-08-04 15:16:42 +08:00

w4a8_dynamic.py

[main][Feature] Support Qwen3 W4A8 quantization (#2060)

2025-07-30 14:57:14 +08:00

w8a8_dynamic.py

[main][Feature] Support Qwen3 W4A8 quantization (#2060)

2025-07-30 14:57:14 +08:00

w8a8.py

[main][Feature] Support Qwen3 W4A8 quantization (#2060)

2025-07-30 14:57:14 +08:00