GitHub / leiwen83 issue stats
Total issues: 52
Total pull requests: 22
Merged pull request: 8
Average time to close issues: 2 months
Average time to close pull requests: about 1 month
Average comments per issue: 3.37
Average comments per pull request: 4.55
Issues created
- vllm-project/vllm: 5
- triton-lang/triton: 4
- ModelTC/lightllm: 4
- NVIDIA/cutlass: 3
- bloomberg/memray: 3
- TabbyML/tabby: 2
- huggingface/text-generation-inference: 2
- openai/triton: 1
- ckkelvinchan/basicvsr-iconvsr: 1
- fasterdecoding/rest: 1
- vinx13/tvm-cuda-int8-benchmark: 1
- NVIDIA/TransformerEngine: 1
- krzysz00/swizzleflow: 1
- huawei-noah/addernet: 1
- jiazhihao/taso: 1
- arm-software/sesr: 1
- deepspeedai/DeepSpeed: 1
- QBDI/QBDI: 1
- MegEngine/MegEngine: 1
- XiaoMi/mace: 1
- NVIDIA/sampleQAT: 1
- siboehm/sgemm_cuda: 1
- pytorch/PiPPy: 1
- codefuse-ai/codefuse-query: 1
- huggingface/accelerate: 1
- uwplse/tensat: 1
- vita-group/agd: 1
- codefuse-ai/codefuse-devops-eval: 1
- mangpo/swizzle-inventor: 1
- open-mmlab/mmflow: 1
- DS3Lab/AC-SGD: 1
- sjtu-ipads/ugache: 1
- amazon-science/cceval: 1
- mlc-ai/mlc-llm: 1
- FMInference/FlexLLMGen: 1
- lm-sys/FastChat: 1
Pull requests created
- vllm-project/vllm: 9
- apache/tvm: 6
- lm-sys/FastChat: 5
- NVIDIA/cutlass: 1
- mlc-ai/relax: 1
Maintainer
Active Maintainer
Issue Author Associations
- None (43, 82.69%)
- Contributor (9, 17.31%)
Pull Request Author Associations
- Contributor (21, 95.45%)
- None (1, 4.55%)
Top Issue Labels
- enhancement (4)
- feature request (4)
- question (3)
- solved (1)
- stale (1)
- new model (1)
- ? - Needs Triage (1)
- inactive-30d (1)
- inactive-90d (1)
- RFC (1)
- keep-open (1)
- unstale (1)
- bug (1)
- training (1)
Top Pull Request Labels
- feature request (1)
- help wanted (1)
- good first issue (1)
- high-priority (1)
- stale (1)