Chayenne 983bfcf386 Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00

..

data_parallel_controller.py

Crash the server correctly during error (#2231)

2024-11-28 00:22:39 -08:00

detokenizer_manager.py

Crash the server correctly during error (#2231)

2024-11-28 00:22:39 -08:00

image_processor.py

Simplify tokenizer manager (#2254)

2024-11-29 02:18:51 -08:00

io_struct.py

Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00

schedule_batch.py

Add a simple torch native attention backend (#2241)

2024-12-01 03:01:25 -08:00

schedule_policy.py

Fix chunked prefill when ignore eos (#2290)

2024-12-01 00:37:53 -08:00

scheduler.py

Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00

session_controller.py

Fix hash collision for multi modal models (#2256)

2024-11-29 03:15:58 -08:00

tokenizer_manager.py

Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00

tp_worker_overlap_thread.py

Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00

tp_worker.py

Online weight updates from torch.distributed (#2279)

2024-12-01 23:23:18 -08:00