vllm/v1/worker/gpu_model_runner.py · f708bd4904ee15bdf9e86503439f2408aa754cda · OpenDAS / vllm_cscc

[BugFix] Fix using `dbo_decode_token_threshold` always (and ignoring... · 984d1849

Lucas Wilkinson authored Sep 26, 2025


[BugFix] Fix using `dbo_decode_token_threshold` always (and ignoring `dbo_prefill_token_threshold`) (#25622)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

984d1849

gpu_model_runner.py 189 KB

Replace gpu_model_runner.py