Levi df7e0fe916 [Bugfix] qwen3-vl-235b-w8a8 load weight ERROR when start service (#4292) ...

### What this PR does / why we need it?
fix qwen3-vl-w8a8 load weight ERROR when start service
0.12.0rc1 can start qwen3-vl-235b-w8a8 by adding this PR

- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

---------

Signed-off-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>

2025-12-15 16:39:58 +08:00

..

compressed_tensors

[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

2025-12-10 15:58:52 +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

quant_config.py

[Bugfix] qwen3-vl-235b-w8a8 load weight ERROR when start service (#4292)

2025-12-15 16:39:58 +08:00

utils.py

[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

2025-12-10 15:58:52 +08:00

w4a4_flatquant_dynamic.py

[main][bugfix] Add 'layer_type' param to get_pergroup_param() for compatibility (#3682)

2025-10-23 21:26:33 +08:00

w4a8_dynamic.py

[perf] replace all_reduce for kv_consumer and support different num_tokens among all ranks (#4983)

2025-12-13 18:59:54 +08:00

w4a16.py

[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

2025-12-10 15:58:52 +08:00

w8a8_dynamic.py

[CI] CI refactor (#4928)

2025-12-14 11:09:56 +08:00

w8a8_pdmix.py

[feature] Support W8A8 PD-Mix Quantization (#4235)

2025-11-30 11:57:26 +08:00

w8a8.py

[Bugfix] Remove ModelSlim-"M4 Quantization". (#4589)

2025-12-01 23:45:02 +08:00