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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Triton][Spec Decode] Non-causal support + relax 3D-launch gate for multi-query verify in unified attention
- [Bugfix][Quantization] Fp8 family: match modules_to_not_convert by substring
- [Kernel] Optimize fused_add_rms_norm with software pipelining
- Add DeepSeek-V4 DCP decode support
- [Experiment][Model Runner V2][Spec Decode] sharded rejection sampling
- [Bug]: [0.22.0] When using Hidden State Extraction, if enable-prefix-caching is turned on, the length of hidden_states obtained will be inconsistent with the length of token_ids.
- [Profiler] Support multiple profiling windows
- [Bugfix] Couple audio+video in mm processor cache for use_audio_in_video (fixes #44538)
- [ROCm][MLA] AITER FP8 ASM prefill backend
- [Bug]: GLM-5 FP8 OOM for long inputs at `flash_mla_cuda.sparse_decode_fwd` on H200
- Docs
- Python not yet supported