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
- [ROCm][Perf] Replace torch.topk in DSA candidate block selection
- [Bugfix][Spec Decode] Defer disposable DeepseekV32 MTP head for modelopt nvfp4
- [Bugfix] Include stable/macros.h in all_reduce_mhc.cu
- [Perf] DiffusionGemma: skip the self-conditioning matmul on a read's last step
- [Bug] NIXL lease reaper strands expired KV blocks behind a heartbeated head entry
- [Docs] Clarify optional serving endpoints
- docs(vllm): fix typos and duplicate word in comments and warning logs
- [Bugfix][Sampler] Fix split top-p masking every token for huge logits (thinking_token_budget + spec decode emits token 0)
- [CI][Bugfix] Set gpu_memory_utilization for the Spark GPQA eval config
- [Feature] [KV Offload] Support sharing SimpleCPUOffload prefix caches across local DP replicas
- Docs
- Python not yet supported