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
- Remove flash_attn dependency
- [Bugfix][Frontend] Omit system_fingerprint key when --fingerprint-mode=none
- [Bug]: DiffusionGemma image input crashes the EngineCore — borrowed Gemma4 methods read `_enable_mm_lora`, which DiffusionGemma never sets
- [Bugfix] Fix two OTel tracing defects: forked-process spans and ignored OTLP protocol
- [Bugfix][Core] Derive trace replay max_tokens from trace length
- [Feature][DSv4.1] Add eager MRV2 decode context parallelism
- [quantization] Add per-token NVFP4 quantization MoE support for ReLU2
- [Bugfix][Model] Fix Qwen4Exp MTP buffer placement, config parsing, and Triton warmup
- [RFC]: Return `routed_experts` on the terminal streaming chunk
- [Perf] Flatten mergeable multi-branch allOf for xgrammar structured output
- Docs
- Python not yet supported