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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: Documented v0.18.0 cu128 release wheel URL returns 404
- Fix incorrect tokenizer source path in RunAI object storage pull (#37836)
- [Feature]: Enable simultaneous generate and embed endpoints in a single vLLM instance
- [Bug]: [Bug]: Kimi-K2.5 on version 0.18.0 results in an keyerror when the pipeline parallelism (PP) is greater than or equal to 2
- [Bug]: chart-helm does not support configuring shared memory (`/dev/shm`)
- [Feature]: Implement `TRITON_MLA_SPARSE` backend for sm80/120/121 support of Sparse MLA
- [Bug]: Shared Expert output is incorrect under Sequence Parallel MoE (EP + TP > 1 + DP > 1) for Qwen3.5 MoE models
- [RFC]: Prefill Context Parallel for Qwen3.5 Hybrid Attention
- [SpecDecode] Add shortcut in rejection sampler for greedy sampling
- [Core] CUDA Checkpoint/Restore — Phase 2: Engine/Executor/API Integration
- Docs
- Python not yet supported