drslark 6a7115fa0d [main][feature] Support quarot for eagle3 without embedding (#7038) ...

### What this PR does / why we need it?
If some `eagle3` model without embed_tokens works with `quarot` target
model, the acceptence rate will drop.
We solve it in this PR.
The relative vllm pr is https://github.com/vllm-project/vllm/pull/36225.

- vLLM main:
4034c3d32e

Signed-off-by: drslark <slarksblood@qq.com>

2026-03-09 10:43:06 +08:00

..

platform

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

worker

[main][feature] Support quarot for eagle3 without embedding (#7038)

2026-03-09 10:43:06 +08:00

__init__.py

[main][feature] Support quarot for eagle3 without embedding (#7038)

2026-03-09 10:43:06 +08:00