Xingkai Yu 44a51afc8a Merge pull request #207 from DestineG/fix-prefill-index-out-of-range ...

fix(scheduler): recalculate num_tokens after allocate to prevent IndexError at model_runner:155

2026-04-25 18:12:43 +08:00

..

block_manager.py

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00

llm_engine.py

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00

model_runner.py

fix(model_runner): correct seqlen_k to chunk boundary in prepare_prefill

2026-04-22 15:13:19 -07:00

scheduler.py

fix(scheduler): recalculate num_tokens after allocate to prevent IndexError

2026-04-20 16:34:27 +08:00

sequence.py

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00