vllm-omni

attention

[BugFix][NPU] Fix Fish Speech S2 Pro NPU support (#7546 )

2026-09-16 11:38:06 -07:00

benchmarks

[CI/Build] Fix Qwen3-Omni Talker benchmark workload (#8057 )

2026-09-24 23:56:53 +08:00

clients

[Bugfix] Fix Nemotron VoiceChat duplex nightly handshake (#7884 )

2026-09-25 17:25:15 +00:00

config

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213 )

2026-10-02 18:03:14 +00:00

core

Merge main into dev/vllm-align for vLLM 0.31 release

2026-10-03 21:05:17 +08:00

deploy

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213 )

2026-10-02 18:03:14 +00:00

diffusion

Merge main into dev/vllm-align for vLLM 0.31 release

2026-10-03 21:05:17 +08:00

distributed

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213 )

2026-10-02 18:03:14 +00:00

engine

Merge main into dev/vllm-align for vLLM 0.31 release

2026-10-03 21:05:17 +08:00

entrypoints

Merge main into dev/vllm-align for vLLM 0.31 release

2026-10-03 21:05:17 +08:00

experimental

[AR-Diffusion] Page in kernel-legal blocks so the default resolution can run (#6481 )

2026-10-02 20:05:04 +08:00

host_weight_runtime

[Bugfix][Core] Clean up failed HWR atomic metadata writes (#6956 )

2026-09-11 09:03:26 +08:00

inputs

rebase: target the official vLLM 0.31.0 release

2026-10-03 21:11:54 +08:00

lora

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

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

metrics

[Model] Optimize MOSS Local 1.5 MRV2 serving and progressive chunks (#8213 )

2026-10-02 18:03:14 +00:00

model_executor

rebase: target the official vLLM 0.31.0 release

2026-10-03 21:11:54 +08:00

model_extras

[Bugfix] Align Ming-Image prompt templates and RNG, fix number of layer to decompose (#8118 )

2026-09-25 22:47:29 +08:00

outputs

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

platforms

[Bugfix] Defer VoxCPM2 NPU patch to avoid platform import cycle (#8330 )

2026-09-30 05:25:36 -07:00

plugins

[Quantization] Migrate GGUF diffusion model support to OOT plugin (#4769 )

2026-07-11 18:48:43 +00:00

profiler

[Enhancement]modify profiling.md (#3051 )

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

protocol

[Frontend][Benchmark] Add duplex performance metrics to refactored full-duplex framework (#7714 )

2026-09-22 03:04:22 -07:00

quantization

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

reasoning

[Rebase] Rebase to vLLM 0.29.0 (#7230 )

2026-09-10 12:08:28 +08:00

sample

update dirs

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

tokenizers

[Model] YuE2: async single-stage synthesis and CUDA graph acceleration (#8407 )

2026-10-02 05:17:06 -07:00

transformers_utils

[Model] Add YuE2-3B text-to-music (model + /v1/audio/speech adapter) (#7886 )

2026-10-01 18:04:31 +08:00

utils

[Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224 )

2026-09-29 15:48:36 +00:00

worker

fix: match vLLM 0.31 generation profiling API

2026-10-03 21:23:18 +08:00

worker_v2

fix: align MRV2 profiling and capture with vLLM 0.31

2026-10-03 22:03:13 +08:00

__init__.py

feat: configure Torch Dynamo recompile limit from environment (#7243 )

2026-09-26 22:54:47 +08:00

data_entry_keys.py

[Core] Extend the shared multi-stage execution framework for mixed V1/MRv2 pipelines (#8184 )

2026-09-29 07:40:57 -07:00

env_override.py

feat: configure Torch Dynamo recompile limit from environment (#7243 )

2026-09-26 22:54:47 +08:00

errors.py

[refactor] Refactor guardrail error handling - add 400 error code (#4297 )

2026-06-11 21:09:24 +00:00

logger.py

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

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

patch.py

[Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224 )

2026-09-29 15:48:36 +00:00

request.py

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

version.py

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

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