xc-llm-ascend

Files

wangxiyuan c8742146d3 [CherryPick] Add unpadded Qwen2.5-VL for verl scenario (#1095 )

Add unpadded Qwen2.5-VL for verl scenario.

When using vllm-ascend for verl scenario, set `USE_OPTIMIZED_QWEN2_5_VL`
(default `1`) to `0` to use unpadded Qwen2.5-VL to avoid errors.

This is cherry-picked from 0.7.3-dev

Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>

2025-06-07 19:45:46 +08:00

__init__.py

[CherryPick] Add unpadded Qwen2.5-VL for verl scenario (#1095 )

2025-06-07 19:45:46 +08:00

deepseek_dbo.py

[perf]: support dual-batch overlap(dbo) for deepseek (#941 )

2025-06-07 16:46:58 +08:00

deepseek_mtp.py

[MTP] follow custom deepseek modeling changes to support graph mode (#636 )

2025-04-28 21:18:53 +08:00

deepseek_v2.py

[perf]Support MOE Multi-stream in Deepseek (#947 )