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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Add a built-in JSON logging formatter
- [Doc] Clarify keep-mode pause and clear_cache semantics
- [Bug]: `allowed_token_ids` + `bad_words` can emit tokens outside the allowlist
- [Bug]: `echo: true` silently stops echoing when the unrelated `return_token_ids: true` is also set
- [Metrics][P/D] Add gauges for KV cache pinned by pending KV transfers
- [Perf][Attention] FA2: split mixed prefill/decode batches into two calls
- [Perf][Model Loader] Skip checkpoint tensors a model does not load before reading them
- [Feature]: ROCm MoRI elastic EP fault tolerance
- [Bugfix][Frontend] Use Anthropic error envelope for /v1/messages validation failures
- [Bug]: Hybrid Mamba/GDN P/D disaggregation is unreachable on CPU — DS conv-layout assert vs the platform's forced SD
- Docs
- Python not yet supported