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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]:Is it possible to install vllm >= 0.18.0 on Ubuntu 20, CUDA 12.6, and Torch 2.11?
- [Bug]: num_blocks division is a no-op in get_moe_wna16_block_config because block_size_k is reassigned first
- [Core] Add VLLM_POISON_DISCARDED_PAGES debug flag for sleep/wake correctness testing
- fix(anthropic): convert tool_reference items to template-safe text
- Fix for Issue 52413: causal_conv1d Alignment Specialization Race Condition
- [ROCm][Perf] Enable medium-skinny dispatch in RDNAHybridW4A16LinearKernel
- [Bugfix] Honor stop strings in beam search
- 魔改vllm: 支持A100 (SM_80) 部署GLM-5.2
- [Debug][V2] Add opt-in rollout layer tensor dumps
- [Bug]: qwen3.8-27b-fp8 toolcall auto stop often
- Docs
- Python not yet supported