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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Tool Parser] Kimi K2: guided decoding for tool_choice="auto" — 75% → 100% schema accuracy
- [Bugfix] Pad Marlin FP8 MoE weight dims to tile alignment under TP > 1
- [Metrics] Temporary band-aid for "Counters can only be incremented by non-negative amounts"
- [Model Runner V2] Introduce num_tokens_for_attn
- [RFC]: Support Registry Mechanism for KVCacheSpec
- [Bug]: dependency `nixl<0.10.0` installs `nixl-cu12==0.10.1`
- [Bugfix] stream failure when model name not in audio endpoints
- Use FLASH_ATTN instead of FLASHINFER for Whisper
- [Feature]: Fast KV Compaction via Attention Matching (50x compression)
- [CPU Backend] Refactor CPU FusedMoE to MK flow
- Docs
- Python not yet supported