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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Pooling Model Performance Optimizations
- [Question][XPU]: Best practices and optimized arguments for running 30B+ models on Intel Arc B580 (Dual GPU) via vLLM-XPU
- Prebuilt vLLM wheels / official images fail on RTX 50-series (Blackwell, SM120/SM121) — "no kernel image" / "sm_120 not compatible"
- [Misc][Harmony] Split harmony_utils.py into domain-specific modules
- Cutlass W4A16 (Machete) Tests
- [Bug]: Fix GLM-OCR text_config model_type handling
- [Performance]: non-optimal performance of `linear` for medium batches
- fix(benchmarks): correct peak output token throughput calculation for speculative decoding
- [Bugfix] Fix Fabric/RDMA attribute queries poisoning global error_code in cumem allocator
- fix(phimoe): use config router_jitter_noise instead of hardcoded jitter_eps
- Docs
- Python not yet supported