Lianmin Zheng cf470fea32 Make token mapping non-blocking in the overlapped mode (#1740)

2024-10-20 23:25:14 -07:00

..

data_parallel_controller.py

Add back data parallelism (#1635)

2024-10-11 07:22:48 -07:00

detokenizer_manager.py

[Minor] Rename no_eos_trim to no_stop_trim (#1661)

2024-10-13 20:30:03 -07:00

image_processor.py

Support qwen2 vl model (#1721)

2024-10-19 21:44:38 -07:00

io_struct.py

Fix failed ci tests on long prompts; Better error messages for embedding models (#1700)

2024-10-17 09:23:29 -07:00

schedule_batch.py

Simplify batch result resolution (#1735)

2024-10-20 19:47:14 -07:00

schedule_policy.py

Returning a per request metric for number of cached_tokens read (#1599)

2024-10-16 11:49:22 -07:00

scheduler.py

Simplify batch result resolution (#1735)

2024-10-20 19:47:14 -07:00

tokenizer_manager.py

Fix failed ci tests on long prompts; Better error messages for embedding models (#1700)

2024-10-17 09:23:29 -07:00

tp_worker_overlap_thread.py

Make token mapping non-blocking in the overlapped mode (#1740)

2024-10-20 23:25:14 -07:00

tp_worker.py

Split the overlapped version of TpModelWorkerClient into a separate file (#1726)

2024-10-20 00:29:29 -07:00