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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Packed Variable Length Speculative Decoding
- [Rust Frontend] Make HTTP request body limit configurable via VLLM_HTTP_MAX_JSON_BODY_SIZE
- [Bug]: disable_flashinfer_q_quantization + fp8 KV + spec decode silently corrupts sliding-window models on SM100 (trtllm-gen); BF16-Q paths also mis-apply q/k/v scales
- [ROCm][Spec Decode] Fix EAGLE3 layer0 acceptance collapse
- [Bug]: VLLM_USE_FASTOKENS=1 raises ImportError - fastokens package missing from Docker image and not listed as pip extra
- [Feature]: Add Prometheus metrics for the multimodal preprocessing pipeline
- [Misc] Add unit test for decode_attention Triton kernels
- [Bug]:MiMo Code mimo_v2_omni.py ERROR
- [Bug][Multi-modal]: Video frames should be paded right by temporal_patch_size
- [Bugfix] Handle list slot_mapping in remaining KV-cache consumers
- Docs
- Python not yet supported