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
- [Bugfix][Core] Copy every overlaid KV view in copy_kv_cache_blocks_inplace
- [Bugfix][KV Offload] Don't pop a verified full-attn eagle prefix chunk
- [Bugfix][OpenAI] Aggregate cached tokens for multi-prompt completions
- [Guard] Assert no prefill in FULL decode-cudagraph replay (#53051)
- [Bug]: --cc.<path>=<value> silently rejected; only -cc short alias works
- [Feature][CPU][Arm]: Add SME1 (FEAT_SME) dispatch for KleidiAI/QMX kernels
- [Bugfix] Validate token budget after disabling chunked prefill
- [Bugfix][KVConnector] Fix Mooncake bootstrap registration hang on timeout
- [Docs][Test] Add GraniteSWA (granite-swash-2b) to batch invariance tested models
- [Tokenizer] Fix tools rendering before system prompt in DeepSeek-V3.2
- Docs
- Python not yet supported