tzhouamandCursor 930c317b2b fix: harden omni weight snapshot downloads ...

Serialize full-repo Hugging Face snapshot materialization with a repo-wide
node lock and retry incomplete snapshots so CI does not race on shared caches.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-06-04 07:54:12 +00:00

..

assets

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

attention

[TTS][Perf] Optimize Fish Speech S2 Pro high-concurrency serving (#3773)

2026-05-27 13:25:49 -05:00

benchmarks

[TTS][Model] support MOSS-TTS series (#3420)

2026-06-02 15:46:01 +08:00

config

[Refactor] Migrate dynin_omni to pipeline registry, drop legacy stage… (#4078)

2026-06-02 21:28:12 +00:00

core

[bugfix] fix streaming input issue after rebase 0.22.0 (#4085)

2026-06-03 16:07:41 +08:00

deploy

[Perf][Qwen3-Omni]Optimize TTFP using initial_codec_chunk_frames (#4054)

2026-06-04 09:08:13 +08:00

diffusion

[Bugfix] harden diffusion model prefetch against transformers v5 shard-resolution race (#4076)

2026-06-04 12:14:25 +08:00

distributed

[bugfix] fix streaming input issue after rebase 0.22.0 (#4085)

2026-06-03 16:07:41 +08:00

engine

[BugFix] Fix the issue of vllm failing to start. (#4105)

2026-06-03 15:44:46 +00:00

entrypoints

Add Cosmos3 action modality (#4102)

2026-06-03 19:30:39 +00:00

inputs

Add Cosmos3 model support (#3454)

2026-06-02 04:04:31 +08:00

lora

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

metrics

[Metrics] Add audio SLOs + cross-stage transfer families + per-(stage, replica) wrap for upstream vllm:* (#3576)

2026-06-01 20:20:48 +08:00

model_executor

fix: harden omni weight snapshot downloads

2026-06-04 07:54:12 +00:00

platforms

[NPU][BugFix] Upgrade parts of ModelRunner to v0.22.0 (#4130)

2026-06-04 03:59:26 +00:00

plugins

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

profiler

[Enhancement]modify profiling.md (#3051)

2026-04-24 16:30:24 +08:00

quantization

[Rebase] Rebase to vllm releases/v0.22.0 (#3891)

2026-06-01 11:08:12 +08:00

sample

update dirs

2025-09-11 15:43:43 +08:00

tokenizers

add support for MammothModa2 model (#336)

2026-03-04 22:52:56 +08:00

transformers_utils

[BugFix] Avoid Voxtral TTS loading error msg (#3951)

2026-05-29 02:35:01 +00:00

utils

[Core] Integrate TrackingArgumentParser (#3369)

2026-06-02 21:56:24 +08:00

worker

[Perf][VoxCPM2] Optimize VoxCPM2 high-concurrency decode throughput. (#3882)

2026-06-03 23:08:32 +08:00

__init__.py

[Bugfix][Refactor] Migrate Voxtral TTS config and parser registry (#3065)

2026-04-25 18:17:25 +08:00

data_entry_keys.py

[Feature] Add precomputed custom voices and Qwen3-TTS ref-context cache (#3492)

2026-05-31 17:51:24 +00:00

logger.py

[BugFix] Failed to print DEBUG level log (#307)

2025-12-15 07:13:36 +00:00

outputs.py

Enable Wan2.2-S2V modeling to vLLM-omni (#2751)

2026-05-06 08:03:48 +08:00

patch.py

[Metrics] Add audio SLOs + cross-stage transfer families + per-(stage, replica) wrap for upstream vllm:* (#3576)

2026-06-01 20:20:48 +08:00

request.py

[Rebase] Rebase to vllm v0.21.0 (#3530)

2026-05-16 18:18:43 +08:00

version.py

[Misc] Warn When vLLM / vLLM-Omni Have Mismatched Versions (#2691)

2026-04-17 20:15:16 +08:00