Daci 2f208db4e9 [Feature] Multimodal Model P / D Separation (#5323) ...

* RouterArgs port str -> int

* fix race condition [is_fetching] causing multiple fetch requests

* bugfix: Delete duplicate input_ids tensor creation

* mm pd splitwise json -> pickle5; multimodal_inputs only pos id;
debuglog f to %s

* fix ENABLE_V1_KVCACHE_SCHEDULER=0 mm model lack pos_id, ...

* update cr

* Apply suggestions from code review

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* pre-commit fix

* rm multimodal_inputs deepcopy & fix rdma_cache_transfer.py tpsize=0

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

2025-12-09 10:47:42 +08:00

..

transfer_factory

[Feature] Multimodal Model P / D Separation (#5323)

2025-12-09 10:47:42 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

cache_data.py

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

cache_messager.py

[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197)

2025-12-04 15:38:43 +08:00

cache_metrics.py

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

cache_transfer_manager.py

[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197)

2025-12-04 15:38:43 +08:00

multimodal_cache_manager.py

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

ops.py

dummy import fd (#5192)

2025-11-24 20:23:07 +08:00

prefix_cache_manager.py

[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197)

2025-12-04 15:38:43 +08:00