vllm/v1/worker/gpu_input_batch.py · 3319a493fcc3e4733382f0dc812184234e9c3dcb · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Core] Reuse created spec tokens lists to mitigate GC cost (#28917) · 3319a493
Jialin Ouyang authored Nov 19, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
3319a493

gpu_input_batch.py 40 KB