Sergey-Zlobin 6a7b3bc29c Qwen3-VL-MoE EAGLE support for vLLM-Ascend (#6327) ...

### What this PR does / why we need it?
Qwen3-VL-MoE EAGLE support for vLLM-Ascend

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
The patch tested with Qwen3-VL-30B-A3B-Instruct model

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8

Signed-off-by: Sergey_Zlobin <sirg_zlobin@mail.ru>

2026-01-29 16:44:30 +08:00

..

__init__.py

Add Medusa speculative decoding support for vllm_ascend (#5668)

2026-01-23 14:14:23 +08:00

eagle_proposer.py

Qwen3-VL-MoE EAGLE support for vLLM-Ascend (#6327)

2026-01-29 16:44:30 +08:00

interface.py

Add Medusa speculative decoding support for vllm_ascend (#5668)

2026-01-23 14:14:23 +08:00

medusa_proposer.py

Add Medusa speculative decoding support for vllm_ascend (#5668)

2026-01-23 14:14:23 +08:00

mtp_proposer.py

[Main2Main] Upgrade vllm commit to 0123 (#6169)

2026-01-27 08:44:36 +08:00

ngram_proposer.py

[Bugfix] Fix in_profile_run in mtp_proposer dummy_run (#5165)

2025-12-18 22:27:47 +08:00

suffix_proposer.py

[Bugfix] Fix in_profile_run in mtp_proposer dummy_run (#5165)

2025-12-18 22:27:47 +08:00