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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: LoRA adapters with PEFT rank_pattern / alpha_pattern are served with the wrong scaling
- [Bug]: Engine fails to start with `--enable-expert-parallel` and `--load-format ipc_cache`; the disk fallback fails too
- [Bugfix][Sampler] Keep tokens top-p must keep in Triton top-k/top-p search
- [Bug]: `--custom-histogram-buckets` rejects a `0` bound, so `vllm:request_num_preemptions` cannot separate never-preempted requests
- [Bugfix][Metrics] Allow zero-valued histogram bucket boundaries for count-based metrics
- [Bugfix][Metrics] Allow a 0 bound in --custom-histogram-buckets
- [ROCm][AMD] GLM5.3 Flash Performance Optimization on gfx950 / MI355X
- [Bugfix][Model] GLM-5.x: load ModelOpt NVFP4 MLA projections into BF16 fused_qkv_a_proj
- [Bugfix][Quantization] NVFP4 linear: apply each fused shard's own global scale
- [DeepSeek-V4-P1] Align dense and masked SiLU FP8 quantization via shared Triton arithmetic
- Docs
- Python not yet supported