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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: [Bug]: meet same thread as registerClien when start_profile
- Pass extra_config to the constructor of LMCacheMPXXXAdapter
- [Bugfix] - Enforce enable_chunked_prefill=False even if long_prefill_token_threshold is set > 0
- [Doc]: Docs audit: CLI, plugins, features, env vars, and auth mismatches
- [Bugfix] Fix streaming tool call args blanked when entire call arrives in one delta
- [Bug]: TRT-LLM FP8 MoE kernel crash on B300 - launchHistogramScoresKernel CUDA error
- Revert "[Quant] add CompressedTensorsW8A8Mxfp8 for linear and MoE layers" (#38815)
- [DRAFT] Remove GGUF quantization
- [Feature]: Implement DELETE /v1/responses/{response_id} for the Responses API
- [Bug]: `reasoning_effort` is silently ignored by nemotron_v3 reasoning parser, and `reasoning_effort: "none"` produces deceptive "hidden cost" output on Nemotron-H
- Docs
- Python not yet supported