Lianmin Zheng e646c5901e Fix logprob in the overlapped mode (#1795)

2024-10-25 11:06:57 -07:00

..

data_parallel_controller.py

[Fix] Fix abort in dp (#1767)

2024-10-23 10:46:29 -07:00

detokenizer_manager.py

[API] add get memory pool size (#1760)

2024-10-23 07:02:29 +00:00

image_processor.py

Llama3.2 vision model support (#1551)

2024-10-21 15:01:21 -07:00

io_struct.py

[API] add get memory pool size (#1760)

2024-10-23 07:02:29 +00:00

schedule_batch.py

Revert "Fix memory leak when doing chunked prefill" (#1797)

2024-10-25 10:24:44 -07:00

schedule_policy.py

Revert "Fix memory leak when doing chunked prefill" (#1797)

2024-10-25 10:24:44 -07:00

scheduler.py

Fix logprob in the overlapped mode (#1795)

2024-10-25 11:06:57 -07:00

tokenizer_manager.py

[API] add get memory pool size (#1760)

2024-10-23 07:02:29 +00:00

tp_worker_overlap_thread.py

Fix logprob in the overlapped mode (#1795)

2024-10-25 11:06:57 -07:00

tp_worker.py

Update max_req_len and max_req_input_len (#1748)

2024-10-21 16:12:04 -07:00