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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Add pre-serve warmup feature for OpenAI API server
- [CI][AMD] Skip tests where models have problems or fails on both HW types
- [ROCm][Attention] Use AITER as fallback for flash_attn_varlen_func
- refactor(envs): migrate vllm/envs.py to pydantic-settings
- [Docker][KVConnector] Build mooncake-transfer-engine from source
- [Model] Add DebertaV2ForSequenceClassification (cross-encoder / reranker)
- Fix Molmo2 image token metadata
- "[Bugfix] release KV blocks for skipped P-ranks ..." accidentally reverted during rebase
- [Bug] DeepSeek-V4-Pro sampling mode produces CJK bad tokens at ~50-75% rate; SGLang is unaffected
- [Refactor] Cleanup batch invariant dead code
- Docs
- Python not yet supported