vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [codex] Optimize FP8 group 128 quantization for Hopper
- [Bugfix] Transformers backend: recompute `mm_token_type_ids` per request for M-RoPE
- [ROCm][Perf] ROCM_ATTN selected over ROCM_AITER_FA for MHA decode despite VLLM_ROCM_USE_AITER=1 (CDNA)
- [ROCm][Perf] Prefer ROCM_AITER_FA over ROCM_ATTN when AITER MHA is enabled
- Add TorchCodec as a video decoding backend
- [Core] Per-worker disk tier + LRU write-back for symmetric multi-node KV cache
- [Model] Add LongCat-Next multimodal model support
- [Model] Support Unlimited OCR
- enable humming wNaM inference for N=[23567] M=[48]
- [Feature]: LoRA support for MiniCPMV4_6ForConditionalGeneration
- Docs
- Python not yet supported