biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support recording expert indices for rollout router replay (#28284)

Browse Source 
Signed-off-by: xhx1022 <1737006628@qq.com>
Signed-off-by: Hongxin Xu <70438206+xhx1022@users.noreply.github.com>
Signed-off-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: arlenxu <arlenxu@tencent.com>
This commit is contained in:
Hongxin Xu
2026-01-12 22:23:04 +08:00
committed by GitHub
parent 0565f1fdec
commit 49e6b86c91
11 changed files with 463 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config/model.py
View File

@@ -198,6 +198,8 @@ class ModelConfig:
graph and always execute the model in eager mode. If False, we will use
CUDA graph and eager execution in hybrid for maximal performance and
flexibility."""
enable_return_routed_experts: bool = False
"""Whether to return routed experts."""
max_logprobs: int = 20
"""Maximum number of log probabilities to return when `logprobs` is
specified in `SamplingParams`. The default value comes the default for the