Sharded, differentiable quantum simulation and training in PyTorch, reaching domestic accelerators through FlagOS.
-
Updated
Oct 21, 2026 - Python
Sharded, differentiable quantum simulation and training in PyTorch, reaching domestic accelerators through FlagOS.
Personal fork for vLLM inference optimization on Iluvatar BI-V150: attention launch policies, profiling, numerical validation and reproducible benchmarks.
FlagOS Track 1 - 20 Triton GPU operators (PyTorch + Triton, Apache-2.0). FlagOS Open Computing Global Challenge, Season 1.
1st place solution for FlagOS Open Computing Global Challenge — Track 3: Long-Context LLM Automatic Data Annotation (Score: 87.24)
High-throughput MiniCPM5-2B inference optimization on FlagOS and FlagGems.
To associate your repository with the flagos topic, visit your repo's landing page and select "manage topics."