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
- [Frontend][Observability] Emit spec-required gen_ai.operation.name (+ gen_ai.request.model) on request spans
- [Bugfix] Pass num_spec to mamba2_state_shape in FalconH1/GraniteMoeHybrid/Zamba2 (spec decode crashes at init)
- [BugFix] Add per-request decode debug logging in v1 output processor
- [Bugfix][Core] Sync reused pinned input buffers under PP batch queue (fixes IMA with sparse MLA + PP)
- Revert "[Bugfix][Frontend][gpt-oss] Recover raw tail when Harmony parser ends non-terminal" (#47379)
- [Doc] Fix stale default CUDA version in GPU install guide
- [KV Connector] Normalize list/tuple KV cache input in register_kv_caches
- [Bugfix] Coerce Python-repr None to JSON null for tool-call args
- [Core][Model] Voxtral realtime: opt-in blank-run penalty to break self-sustained silence ruts
- [Attention] TRITON_MLA_SPARSE backend for SM80/SM121 sparse MLA (rebase & takeover of #38476)
- Docs
- Python not yet supported