wangyibo1005 25baf6df09 [Feature]EPLB:Adapt DispatchGmmCombineDecode operator to eplb tensor list and expert token numbers (#5552) ...

#### What this PR does / why we need it?
This PR adapt DispatchGmmCombineDecode operator to eplb tensor list and
expert token numbers.

This operator support gmm1, gmm2, gmm1Scale and gmm2Scale in format of
list.
This operator support couting how many token each local expert recieves
by expertTokensNum .


- vLLM version: v0.13.0
- vLLM main:
7157596103

More info about this operator, please refer to RFC: issue
https://github.com/vllm-project/vllm-ascend/issues/5476

2026-01-07 11:23:42 +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

[MM][Bugfix] Update hf_config to hf_text_config (#5319)

2026-01-06 16:41:39 +08:00

utils.py

[quantization] Add w8a16 quantization support (#4541)

2025-12-24 19:49:32 +08:00

w4a4_flatquant_dynamic.py

[refactor] refactor weight trans nz and transpose (#4878)

2025-12-19 14:27:24 +08:00

w4a8_dynamic.py

Bugfix: Align expert map shapes with redundant experts in EPLB adjustment (#5285)

2026-01-06 17:22:36 +08:00

w4a16.py

Bugfix: Align expert map shapes with redundant experts in EPLB adjustment (#5285)

2026-01-06 17:22:36 +08:00

w8a8_dynamic.py

[Feature]EPLB:Adapt DispatchGmmCombineDecode operator to eplb tensor list and expert token numbers (#5552)

2026-01-07 11:23:42 +08:00

w8a8_pdmix.py

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

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

w8a8.py

[refactor] Remove unnecessary attributes from set_ascend_forward_context (#5204)

2025-12-23 08:49:52 +08:00

w8a16.py

[quantization] Add w8a16 quantization support (#4541)

2025-12-24 19:49:32 +08:00