vllm/v1/worker/tpu_model_runner.py · b3f2fddd172cef23b42ffaf6c226877b6588964c · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[TPU][V1] Fix exponential padding when `max-num-batched-tokens` is not a power of 2 (#16596) · b3f2fddd
Nicolò Lucchesi authored Apr 14, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
b3f2fddd

tpu_model_runner.py 47.2 KB