Hanming Lu e61dabf5e4 [Qwen3-next] support mamba radix cache for overlap scheduler (#14792)

2025-12-14 18:54:16 -08:00

..

ascend

…

base

[PD] Clarify init method docstrings for kvsender and kvreceiver (#13476)

2025-11-18 12:20:19 +08:00

common

Enhance prefill PP node robustness (#14494)

2025-12-06 18:00:54 -08:00

fake

…

mooncake

[PD] Add decode PP event loop for PD disaggregation (#14945)

2025-12-12 20:15:00 +08:00

nixl

[PP Prefill][NIXL] Fix PP mode transfer completion tracking to wait for all ranks (#15027)

2025-12-13 00:55:28 -08:00

decode_kvcache_offload_manager.py

…

decode_schedule_batch_mixin.py

[Spec v2] Remove allocate_lens and enable over-allocation (#13478)

2025-11-22 22:49:10 +08:00

decode.py

[Qwen3-next] support mamba radix cache for overlap scheduler (#14792)

2025-12-14 18:54:16 -08:00

encode_receiver.py

feat: support EPD disaggregation (#12263)

2025-12-14 22:30:08 +08:00

encode_server.py

feat: support EPD disaggregation (#12263)

2025-12-14 22:30:08 +08:00

kv_events.py

…

prefill.py

[PP] Refactor PP to async mode (#11852)

2025-12-12 12:54:16 +08:00

utils.py

…