vllm-project/vllm-omni

[New Model]: DreamX-World about 8 hours ago

help wanted new model high priority diffusion world model

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Unify example model usage — migrate all special-usage examples to standard task examples + declarative model_extras about 12 hours ago

help wanted good first issue high priority critical

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

Codebase cleanup audit: dead code, config drift, and packaging robustness about 16 hours ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Good First Issue]: Add vendor-organized community recipes for “run model X on hardware Y for task Z” in vLLM-Omni 1 day ago

help wanted good first issue high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC/Bug] Improve diffusion worker/engine control-plane reliability and output contracts 1 day ago

bug help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model] Add TADA (Hume AI) TTS model support 2 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Support NVIDIA Alpamayo 1.5 (Reasoning VLA for Autonomous Driving) in vLLM-Omni 2 days ago

help wanted world model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Aligned with vllm 0.23.0 now][RFC]: vLLM-Omni 2026 Q2 Roadmap 2 days ago

help wanted good first issue roadmap

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: World Model Support 3 days ago

help wanted good first issue new model high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: [Cosmos3 optimization] Feature Support, Quantilization, Hardware Recipes, and Scenario Optimization 3 days ago

help wanted good first issue high priority Hardware Plugin diffusion critical

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: vLLM-Omni NPU 2026 Q2 Roadmap 3 days ago

help wanted good first issue NPU high priority Hardware Plugin

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: dots.tts (rednote-hilab) — continuous-AR 48kHz zero-shot voice cloning 3 days ago

help wanted good first issue new model tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Performance]: Per-request Python preprocess loop dominates decode step time at high concurrency (8.5 ms of a 10.9 ms step at 32 requests) — also a frame-cadence blocker for realtime/duplex 4 days ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Continuous Quantization Support 5 days ago

help wanted good first issue high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Decouple vllm-omni GGUF quantization from upstream vllm#39583 6 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: TTS Development Roadmap - Q2 2026 7 days ago

help wanted good first issue high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC] Full-Duplex Session Architecture for vLLM-OMNI 7 days ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: NVIDIA ModelOpt Quantized Diffusion & Video Model Deployment in vLLM-OMNI 8 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: inclusionAI/Ming-omni-tts-16.8B-A3B 8 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Add PersonaPlex (nvidia/personaplex-7b-v1) MVP support 8 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: SenseNova-U1Optimization Roadmap 8 days ago

good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: jd-opensource/JoyAI-Image-Edit 9 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Add JoyAI-Echo (LTX-2.3-derived multi-shot T2V+Audio) 9 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Audio-Omni 9 days ago

help wanted good first issue new model diffusion tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Support Container Image Format -> ARM64 11 days ago

help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Perf]: Voxcpm2 performance improvement 11 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Support Model FLOPs Utilization (MFU) Metrics for Diffusion Models (DiTs) 11 days ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: HiDream-O1-Image 11 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Baidu NAVA video 12 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[CI/Test] Add Fish Speech TTS e2e test (no e2e coverage in any pipeline tier) 12 days ago

good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Support Loading Original (Non-Diffusers) PAI/Wan2.2-VACE-Fun-A14B Checkpoint 13 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Can support the model wan2.2-fun-a14b-inp use the tool vllm-omni? 13 days ago

good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Sana-WM 14 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Bagel deployment 14 days ago

enhancement help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: vLLM-Omni XPU 2026 Q2 Roadmap 16 days ago

help wanted Hardware Plugin roadmap

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: circlestone-labs/Anima 17 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC][calling for help from the community]: Large-Scale Multi-Stage Serving Architecture for vLLM-Omni 17 days ago

enhancement help wanted high priority roadmap

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]:Step Audio 2 18 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Add word-level timestamps to TTS streaming output via shared forced aligner 18 days ago

enhancement good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: add HunyuanVideo-I2V 19 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Rename ar_stop_token_ids to a more descriptive name 20 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: VibeVoice 20 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Support Wan-AI/Wan2.2-S2V-14B in vllm-omni 22 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[help wanted][Feature]: Claude Code skills for model integration, benchmarking, and PR workflow 22 days ago

enhancement help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

Consider using pre-built Flash Attention kernels via `kernels` 22 days ago

help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Kernel Optimization for Diffusion DiT and MoE LLM 25 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: deepseek-janus 26 days ago

help wanted new model high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Omni-Diffusion 27 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Encoder Embedding Data Sharing for Disaggregated Omni-Modality Inference 27 days ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Enable NPU CI Tests 27 days ago

help wanted NPU

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Bug] OmniVoice online-serving example fails with HTTP 400 from hardcoded voice "default" 28 days ago

bug good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: OpenMOSS-Team/MOVA-720p 28 days ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model] PrismAudio (Video-to-Audio Generation) 29 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: bitdance 29 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model] Fun-CineForge (Zero-Shot Movie Dubbing) 29 days ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: MiniMind-O (0.1B / 0.3B-A0.1B end-to-end Omni with Thinker-Talker + Mimi codec) 29 days ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: HunyuanImage Model deployment optimization 29 days ago

help wanted good first issue new model high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: SoulX-Singer — Open-Source Zero-Shot Singing Voice Synthesis (Soul AI Lab) 29 days ago

help wanted good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Pipeline Parallelism & Stream Batch for Real-Time Video Generation 30 days ago

help wanted good first issue high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: stabilityai/stable-audio-3-medium (DiT text-to-audio for music and SFX) 30 days ago

good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Plugin-based Sparse Attention Interface for DiT Modules about 1 month ago

help wanted good first issue high priority diffusion

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Lance from ByteDance about 1 month ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Continuous Recipe Support for Diffusion Models about 1 month ago

help wanted good first issue diffusion

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: vLLM-Omni Diffusion Module — Q2 2026 Roadmap about 1 month ago

enhancement good first issue high priority diffusion

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Qwen3-TTS high-throughput hardening about 1 month ago

help wanted high priority tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Diffusion Offline Examples Docs & Test about 1 month ago

documentation enhancement help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: SongGeneration 2 / LeVo 2 (Tencent AI Lab) — Hybrid LLM-Diffusion Full-Song Generation about 1 month ago

help wanted good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: HiDream-O1-Image about 1 month ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

vLLM-Omni Model Support about 1 month ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Mooncake and vLLM-Omni Collaboration Roadmap about 1 month ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Vevo2 — Unified Controllable AR + Flow-Matching for Speech and Singing Voice Generation about 1 month ago

help wanted good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: SongGen — Single-Stage Auto-Regressive Transformer for Text-to-Song about 1 month ago

help wanted good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: LingBot-World-Fast — Interactive video world model port about 1 month ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Followup] Deploy YAML field ownership: stage-level defaults, user knobs, and model-owned config about 1 month ago

good first issue frontend

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: OpenMOSS-Team/MOSS-TTS about 2 months ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Step Audio EditX about 2 months ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: [Meta] Tuna series about 2 months ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: FLUX.2-dev Model Acceleration Support about 2 months ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: Omni model openbmb/MiniCPM-o-4_5 about 2 months ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Bug]: The field `profiler_config` in deploy yaml can't be passed correctly about 2 months ago

bug help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Support VAE as a Separate Stage to Reduce GPU Memory Pressure in Diffusion Pipelines about 2 months ago

enhancement help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Performance] Qwen-Image双卡配置下单张图片生成时间未优化 - TP2/DP2/PP2性能问题 about 2 months ago

help wanted good first issue NPU

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: VoxCPM2 about 2 months ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: diffusion engine clean up about 2 months ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Bug] CUDNN_ATTN crashes on LTX-2.0 audio attention under torch.compile (symbolic head_dim) about 2 months ago

help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: LTX-2.3 about 2 months ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: vLLM-Omni 2026 Q1 Roadmap about 2 months ago

documentation help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: [UX][Metrics] Improve vLLM-Omni Metrics UX about 2 months ago

help wanted good first issue high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC] Sentinel-default precedence for stage engine args about 2 months ago

help wanted high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: GLM-Image Performance Optimization about 2 months ago

help wanted good first issue NPU high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Bug]: Use SageAttention backend Wan2.2 and Hunyuan-Video Quality Crash about 2 months ago

bug help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Bug]: Qwen3-TTS-CustomVoice ignores fixed seed setting 2 months ago

bug help wanted good first issue tts

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Wan2.2 Performance Optimization Roadmap on vLLM-Omni 2 months ago

help wanted good first issue NPU high priority

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Abort request when http disconnects 2 months ago

enhancement help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[New Model]: https://huggingface.co/zai-org/GLM-TTS 2 months ago

help wanted good first issue new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: TTS Development Roadmap - March 2026 2 months ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Enable Prefix Caching with Hidden-State I/O (Multi-round / Service Scenarios) 2 months ago

enhancement help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Support Wan2.2-I2V-A14B Model in vllm-omni Multimodal Generation Framework 2 months ago

help wanted

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[Feature]: Auto-syncing example/*/*/README.md to docs/user_guide/examples/*/*.md 2 months ago

help wanted good first issue

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

[RFC]: Support 3D World Model (VGGT, etc.) 2 months ago

help wanted new model

vllm-project/vllm-omni

3.2K

A framework for efficient model inference with omni-modality models

Python

#audio-generation#diffusion#image-generation#inference#model-serving#multimodal#pytorch#transformer#video-generation

Open Issues Need Help