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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: Intel Xeon Prefill Decode Disaggregation
- [Bug] FP8 block-quant loader rejects artifacts using 'weight_scale' rather than 'weight_scale_inv' naming
- [Bug]: TurboQuant crashes on T4/Turing (SM75) — FlashAttention capability not checked
- [Bug]: Prefix caching fails for incremental multimodal requests on Mamba-Attention hybrid models (Qwen3.5)
- Optimize DFlash context KV cache updates
- [Bug]: Qwen3-VL-2B-Instruct Geo3K accuracy score lower than SGLang with deterministic sampling
- [MRV2][KVCache] Optimize block mapping with np array
- [Bugfix] Fix KeyError on KV-shared consumer layer in get_attn_backends_for_group
- [CI/Perf] Invalid JSON in serving benchmark config
- [Bug]: MoE+DP — zero-token-scheduled step skips coordinate_batch_across_dp for ray/mp DP backends → ~T+1h NCCL reduce_scatter deadlock
- Docs
- Python not yet supported