Yuan Luoandluoyuan.luo 53846746bf [VLM] Fix CUDA IPC OOM (#16118) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2026-01-07 11:30:35 +08:00

..

async_dynamic_batch_tokenizer.py

…

async_mm_data_processor.py

…

cache_controller.py

[HiCache] Add PP Support with suffix pp rank (#15175)

2026-01-03 13:49:21 +08:00

configure_logging.py

…

data_parallel_controller.py

Revert "[FEAT] optimize tensor zmq transfer for multimodal inputs" (#16386)

2026-01-04 22:05:26 -08:00

detokenizer_manager.py

Support returning customized info (#16144)

2026-01-02 15:32:18 +08:00

disagg_service.py

…

io_struct.py

[VLM] Support request level max_dynamic_patch for OpenAI request (#16268)

2026-01-04 13:04:43 +08:00

mm_utils.py

EVS Framework: Support NemotronH_Nano_VL_V2 (#14051)

2026-01-05 16:18:07 +08:00

multi_tokenizer_mixin.py

Revert "[FEAT] optimize tensor zmq transfer for multimodal inputs" (#16386)

2026-01-04 22:05:26 -08:00

multimodal_processor.py

…

overlap_utils.py

feat(SpecEagleV2): add standalone_worker_v2 (#12625)

2025-12-30 17:55:04 +08:00

prefill_delayer.py

Tiny add metrics for prefill delayer (#16603)

2026-01-07 09:53:52 +08:00

request_metrics_exporter.py

[Auto Sync] Update request_metrics_exporter.py (20251230) (#16183)

2025-12-30 11:09:41 -08:00

schedule_batch.py

[VLM] Fix CUDA IPC OOM (#16118)

2026-01-07 11:30:35 +08:00

schedule_policy.py

Move swa memory pool to a seperate file (#16347)

2026-01-04 22:39:30 +08:00

scheduler_dp_attn_mixin.py

Move log_prefill_stats_late to correct location in PP mode (#15946)

2025-12-31 12:00:24 +08:00

scheduler_input_blocker.py

…

scheduler_metrics_mixin.py

Fix metrics (#15998)

2025-12-28 05:03:49 -08:00

scheduler_output_processor_mixin.py

Support returning customized info (#16144)

2026-01-02 15:32:18 +08:00

scheduler_pp_mixin.py

Move log_prefill_stats_late to correct location in PP mode (#15946)

2025-12-31 12:00:24 +08:00

scheduler_profiler_mixin.py

hotfix: add type hints to scheduler mixins (#15916)

2025-12-26 17:08:11 -08:00

scheduler_recv_skipper.py

…

scheduler_runtime_checker_mixin.py

…

scheduler_update_weights_mixin.py

…

scheduler.py

Tiny add metrics for prefill delayer (#16603)

2026-01-07 09:53:52 +08:00

session_controller.py

…

template_manager.py

…

tokenizer_communicator_mixin.py

Revert "[FEAT] optimize tensor zmq transfer for multimodal inputs" (#16386)

2026-01-04 22:05:26 -08:00

tokenizer_manager_multiitem_mixin.py

Add a test case for crash dump (#15905)

2025-12-26 19:39:28 -08:00

tokenizer_manager.py

[Auto Sync] Update tokenizer_manager.py (20260105) (#16477)

2026-01-05 14:06:03 -08:00

tp_worker.py

Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00

utils.py

…