python/sglang/srt/managers/tp_worker.py · b0524c3789725642c3dd93323d47b18b9ba77a51 · change / sglang · GitLab

Find file Blame History Permalink

Eagle speculative decoding part 2: Fix cuda graph + DP attention hanging (#2684) · b0524c37
Lianmin Zheng authored Dec 31, 2024
```
Co-authored-by: yukavio <kavioyu@gmail.com>
```
b0524c37

tp_worker.py 7.58 KB