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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Model] Align Nemotron vision compute dtype
- [CI] Shard (H200 MIG 35GB) PyTorch Compilation + (MI300) mirror into whole coverage units
- [requirements]: update the mooncake-transfer-engine wheel
- [CI] Shard (L4) Pipeline + Context Parallelism + (MI250) mirror into whole coverage units
- [WIP][Sampling] Add adaptive verification support to batch-sharded sampling
- [CI][ROCm] Provide source artifacts for Python-only compilation
- [Model] Update RADIO vision encoder to match the current Transformers version
- [Bug]: NIXL P/D mis-transfers a GQA draft's KV (e.g. DFlash) under an MLA target with prefill TP < decode TP
- [Bugfix][KV Connector][NIXL] Shard a GQA draft's KV by head under an MLA target
- [KV Connector] Fix DecodeBench fp8 fill values and add a startup fill mode
- Docs
- Python not yet supported