Sy03 2c73cf3522 [Perf] Fix Qwen3-TTS latency regression (#3485) ...

Signed-off-by: Sy03 <1370724210@qq.com>

2026-05-10 23:07:38 +00:00

..

__init__.py

Initial vLLM-omni repository structure

2025-09-11 14:32:51 +08:00

base.py

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365)

2026-05-07 23:23:59 +08:00

gpu_ar_model_runner.py

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365)

2026-05-07 23:23:59 +08:00

gpu_ar_worker.py

[MUSA][Feat] torch.accelerator support (#3101)

2026-04-24 15:31:45 +00:00

gpu_generation_model_runner.py

[Rebase] Rebase to vllm 0.20.0 (#3232)

2026-04-30 09:56:59 +12:00

gpu_generation_worker.py

[MUSA][Feat] torch.accelerator support (#3101)

2026-04-24 15:31:45 +00:00

gpu_memory_utils.py

Process-Scoped GPU Memory Accounting (#1204)

2026-02-08 22:43:02 +08:00

gpu_model_runner.py

[Bugfix] Propagate seed to Qwen3-TTS Fast AR sampler (#3350)

2026-05-05 14:57:55 -04:00

mixins.py

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

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

omni_connector_model_runner_mixin.py

[Perf] Fix Qwen3-TTS latency regression (#3485)

2026-05-10 23:07:38 +00:00

payload_span.py

[core]refactor communication layer: PR1(Added Refactor Infra Only) (#1555)

2026-04-13 16:01:14 +08:00