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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [kv_offload] Fix bare Exception types and add FilterReusedOffloadingManager tests
- [Bug]: Tesla T4 GPU - triton.runtime.errors.OutOfResources: out of resource: shared memory, Required: 81920, Hardware limit: 65536. Reducing block sizes or `num_stages`
- [Bug]: Misleading error message for FP8 quantization: refers to CUDA version instead of GPU compute capability
- [Bug]: GLM-4.7-Flash does not return tool_calls field in vLLM 0.16.0 even with --tool-call-parser glm47
- [Bug]: Qwen3-Coder-Next-FP8 start error wifh tp=8 on H100
- [Perf] recreate torch profiler wrapper for each new profiling session to avoid slow starts
- [Bug]: ROCm: tries to allocate 192GB VRAM for Qwen3.5 0.8B
- [Bug]: CUDA illegal memory access on GPTQ Marlin
- [Bug]: No sm_121 (Blackwell) support on aarch64 — NVIDIA DGX Spark / Acer GN100
- [Bugfix] Clear error message for FP8 torchao quantization on unsupported GPUs
- Docs
- Python not yet supported