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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: fp8 KV cache for the Ampere sparse-MLA path (TRITON_MLA_SPARSE) via software dequant
- [Bugfix][Spec Decode] DSpark: store draft KV cache in model dtype for MLA-only cache layouts; fail fast on DCP
- [ROCm][Quant] Requantize serialized MXFP8 linears to FP8 PTPC
- [Bugfix] Wire up weight offloader in V2 Model Runner (`--cpu-offload-gb` was silently a no-op)
- [Bug]: glm-5.2-fp8 with --kvcache-dtype fp8 with h20-3e with dspark error
- [Bugfix] Clamp spec-decode state index load for zero num_accepted_tokens in GDN kernels
- fix(security): validate GPTQ kernel inputs to prevent OOB reads
- Update README with new 'evil' section
- [Doc] Add Nika to serving integrations
- [Doc] Fix stale ModelOpt test instructions in modelopt.md
- Docs
- Python not yet supported