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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Model] MiMo-V2: support TP > num_kv_heads for the fused FP8 QKV projection
- [Rust Frontend] Add Rust Apertus tool parser
- [BugFix] Fix decode-phase blocks not stored in CPU KV cache offloading
- [ROCm][Bugfix] window-correct shuffled fp8 decode for SWA layers
- [Bug]: Llama-4-Scout-FP8 tool calls left in content (not parsed into tool_calls) — pythonic parser vs JSON output mismatch, breaks Claude Code
- [XPU] All-to-all Expert-Parallellism backend for batched MoE
- [BugFix] Rebuild InputBatch when max_model_len is auto-reduced
- [Fix] get_num_blocks_to_allocate provides wrong block count while external cache hit
- [KV Connector][Hybrid] Enable GDN all-mode Mamba prefix caching with Mooncake Store retention
- [MoE] [MoE Refactor] Migrate int8 w4a8int8 oracle 37753
- Docs
- Python not yet supported