vllm-project/vllm-omni

[Feature]: Support VAE as a Separate Stage to Reduce GPU Memory Pressure in Diffusion Pipelines about 5 hours ago

enhancement help wanted

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 about 6 hours 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]: Support Wan2.2-I2V-A14B Model in vllm-omni Multimodal Generation Framework about 8 hours 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]: SoulX-Duplug-0.6B (Soul-AILab/SoulX-Duplug-0.6B) about 9 hours 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

vLLM-Omni Model Support about 15 hours 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]: HunYuanImage Diffusion Optimization Tracking about 15 hours 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]: Omni Model 2026 Q1 Roadmap about 15 hours 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

[RFC]: Qwen3-TTS Production Ready - February Milestone about 17 hours ago

enhancement 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

[Feature]: Can support the model wan2.2-fun-a14b-inp use the tool vllm-omni? about 21 hours 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]: LTX-2.3 about 21 hours 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]: Exit on OOM about 21 hours 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] AudioX (Multimodal Audio Generation) 1 day 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 2 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] Fun-CineForge (Zero-Shot Movie Dubbing) 3 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] Add TADA (Hume AI) TTS model support 3 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] Covo-Audio-Chat (End-to-End Audio LLM) 4 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]: Step-Audio-R1.1 4 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]: vLLM-Omni 2026 Q1 Roadmap 5 days 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

[New Model]: VoXtream2 (herimor/voxtream2) 5 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]: HyperCLOVAX-SEED-Omni-8B 5 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]: https://huggingface.co/zai-org/GLM-TTS 5 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] F5-TTS (flow-matching DiT-based TTS) 5 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]: TTS Development Roadmap - March 2026 5 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 3.0 deployment 6 days ago

enhancement 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]: Diffusion Offline Examples Docs & Test 6 days 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]: Index-AniSora (Bilibili) 6 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] Q1 Quantization Support 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

[Feature]: Accuracy Benchmarks for T2I and I2I Generation 8 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

[RFC]: Bagel deployment 9 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

[Feature]: NextStep1.1 quantized model is not supported 9 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

[RFC]: Ray Connector 10 days ago

enhancement 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]: FLUX.2-dev Model Acceleration Support 11 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]: DreamID-V from ByteDance Seed 11 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]: Refactoring Qwen3-Omni and Qwen2.5-Omni thinker 12 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

[New Model]: Kimi-Audio-7B 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

[Performance]: High VRAM overhead in Diffusion Stage and ineffectiveness of `gpu_memory_utilization` 12 days ago

enhancement 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 Multimodal Output Channel & Simplify Output Processor 13 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

[Performance]: Large IPC serialization overhead in diffusion video generation for large videos 14 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]: Enable Prefix Caching with Hidden-State I/O (Multi-round / Service Scenarios) 14 days 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]: Improving FP8 Support for Qwen3-Omni in vLLM-Omni 15 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]: Low-Precision Quantization (MXFP4) Support for Multimodal Models in vLLM-Omni 15 days ago

enhancement 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

[Bug]: The speed of compile mode does not perform well during parallel inference 17 days 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

[New Model] CosyVoice 2/3 (LLM-based streaming TTS) 19 days ago

AI Summary: The GitHub issue proposes adding support for CosyVoice 2/3, a popular LLM-based streaming Text-to-Speech (TTS) model. It leverages a Qwen2.5-0.5B backbone to generate speech tokens via Finite Scalar Quantization (FSQ), followed by causal flow matching for audio synthesis. The integration aims to benefit from `vllm-omni`'s existing transformer optimizations, offering low-latency streaming and multi-language support.

Complexity: 4/5

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]: General TTS Model Implementation 22 days ago

enhancement 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]: inclusionAI/Ming-omni-tts-16.8B-A3B 22 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]: Refactor Output Processor 22 days 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]: HunyuanVideo-1.5 25 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 25 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]: VibeVoice 26 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]: vLLM-Omni Multi-Stage CFG Support 29 days ago

enhancement 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]: Fun-CosyVoice3-0.5B 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]: Owen777/UltraFlux-v1 29 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]: OmniGen2 30 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]: FLUX.1-Kontext-dev 30 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]: bytedance-research/MammothModa2-Preview 30 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]: Offline inference supports async_chunk about 1 month 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]: vllm-omni CI/CD plan about 1 month ago

enhancement 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]: OpenMOSS-Team/MOSS-TTS 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]: Wan2.2 Performance Optimization Roadmap on vLLM-Omni about 1 month 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

[Feature]: Support Container Image Format -> ARM64 about 1 month 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]: Rebase Additional Information into Model Intermediate Buffer about 1 month ago

enhancement 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 PersonaPlex (nvidia/personaplex-7b-v1) MVP support 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]: Abort request when http disconnects about 1 month 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

[Feature]: Support for Full Shared Data Parallel (FSDP) in vLLM-Omni about 1 month ago

enhancement 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

[Bug]: huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name' about 1 month 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

[New Model]: OpenMOSS-Team/MOVA-720p 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]: Skywork / SkyReels 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]: Process-Scoped GPU Memory Accounting for Concurrent Omni Stage Initialization in vLLM about 2 months ago

enhancement 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]: Diffusion chat completion failed: 'numpy.ndarray' object has no attribute 'save' about 2 months ago

bug 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

[Bug]: Qwen3-omni，if flash-atten is installed, setting enforce-eager to false, the instance failed to start. 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

[Feature]: ComfyUI Intergration 2 months ago

enhancement 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

[Feature]: Online serving support cfg args 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

[Doc]: Need guidance on Qwen-Image-Layered online serving 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]: DiT model and feature support enhancement 2 months ago

AI Summary: This RFC proposes enhancing vLLM-Omni's support for state-of-the-art DiT (Diffusion Transformer) models, encompassing image, video, and any-to-any generation. It aims to extend the existing Qwen-Image implementation and actively seeks community contributions for this rapidly evolving domain.

Complexity: 4/5

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

[Bug]: TeaCache Not Supported by LongCat-Image, LongCat-Image-Edit, and Tongyi-MAI/Z-Image-Turbo 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

[New Model]: Lightricks/LTX-2 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]: LLADA 2.0 Series 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]: LongCat-Flash-Omni 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]: ByteDance-Seed/BAGEL-7B-MoT 3 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

[Feature]: LoRA adapter support for vLLM alignment 3 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]: Support torch profiler 3 months ago

AI Summary: This GitHub issue requests support for the PyTorch profiler in vLLM-Omni, as its current absence makes performance bottleneck analysis difficult for multimodal/diffusion workloads. Users have confirmed that setting `profile=True` or configuring `VLLM_TORCH_PROFILER_DIR` does not activate the profiler. Maintainers acknowledge this as a planned but unscheduled feature.

Complexity: 4/5

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]: stepfun-ai/NextStep-1.1 3 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

[Roadmap]: preparing for v0.12.0 release 3 months 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

[RFC]: Proposal for Supporting Context Parallelism (RingAttention) and Parallelism Terminology Alignment in vLLM-Omni 3 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

[Bug]: OOM of Qwen-Image (2048px) generation after rebasae to v0.12.0 3 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

[New Model]: Step Audio EditX 3 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

[Performance]: Use rope kernel to replace torch native code 3 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

[Performance]: Tensor.cat in OmniRequestState.add_multimodal_tensor is slow 3 months 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]:Step Audio 2 3 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]: Fun-Audio-Chat support 3 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]: HunyuanImage-3.0 support 3 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]: add HunyuanVideo-I2V 3 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]: LongCat-Image & LongCat-Image-Edit 3 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

[Bug]: Shape mismatch when using TeaCache for accelerating Qwen Image Edit 2509 3 months ago

bug 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]: Diffusion Chunked Scheduling RFC (Draft) 3 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]: stabilityai/stable-audio-open-1.0 3 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]: FunAudioLLM/Fun-ASR-Nano-2512 3 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]: Wan-AI/Wan2.2-I2V-A14B-Diffusers 3 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]: Stable Diffusion 3 3 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

[Feature][RL]: Support Model weight offload, reload and sync model weight & Offload DIT cache 3 months 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

Open Issues Need Help