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
- [Perf][SM100] Use TGV for small-batch BF16 output projections
- [Kernels][Fusion] Fused silu mul per token quant
- [Fusion] Apply manual activation+quant fusion to Granite and EXAONE 4.0
- [Bugfix] Reject padding when the tokenizer has no pad token
- [Refactor][MoE] Migrate Quark static INT8 to the MoE oracle
- [Bug]: `--hf-overrides '{"rope_scaling": ...}'` drops `rope_theta` under Transformers v5; models without a per-file default silently run with base 10000
- [Bugfix] Preserve RoPE base parameters in rope_scaling overrides
- [Bugfix][DeepGEMM] Restore SM12x alignment behavior for grouped GEMMs
- [CLI] Add configurable help views
- [Bugfix] Return bound ephemeral port when VLLM_PORT is zero
- Docs
- Python not yet supported