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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf][DSv4.1] Mono: merge K2(l) and K1(l + 1) into one launch at TP8
- [Rust Frontend] Export cache configuration metrics
- [Refactor] Migrate FlashInfer NVLink two-sided to MoEEpCommunication
- [Bug][Spec Decode] DSD K=0: draft-KV retention cost under batch-size ladders + tier-edge release design (with high-concurrency corroboration for #53426)
- fixing up the MCP Tool discovery
- [Perf][Model] Qwen4Exp QSA: compact grid for indexer prefill scoring
- [Perf][Model] Qwen4Exp QSA: SM120 launch config for indexer prefill scoring
- [Docs] Document hybrid NIXL startup requirements
- [ROCm][Perf][Qwen4Exp] Tune QSA sparse GQA and indexer on gfx942 and gfx950
- [Bugfix][ROCm][Qwen4Exp] Bind the opaque SP wrapper in the MTP draft
- Docs
- Python not yet supported