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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][Kernel] Use bf16 shared staging in mHC pre TileLang kernel
- Add extra_labelnames to PrometheusStatLogger for extensibility
- [CT] Fix weight processing for FP8 Marlin
- [Core] Per-layer parallelism policy + TPA-GQA on FlashAttention
- Fix ITL accuracy when server batches multiple tokens per SSE chunk
- Revert "[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support" (#39568)
- [Perf][Qwen3.5] Fuse GDN linear_attn qkv|z|b|a into a single GEMM
- [Examples] Add NixlConnector support to disagg_proxy_demo
- Add release_kv_cache API
- [Bug]: TurboQuant decode attention: workspace allocation not sized during warmup → AssertionError on first decode after lock_workspace()
- Docs
- Python not yet supported