» Tag
llm-training
2 postsCross-tokenizer distillation can silently erase 85% of teacher signal
Naive logit projection across mismatched tokenizers can erase 85% of teacher information; chain-rule conditioning restores retention to 86%.
Flash-MSA: Open-Source Sparse Attention Kernels for Fast Training
Flash-MSA brings open-source CuTeDSL training kernels for MiniMax Sparse Attention on Hopper/Blackwell GPUs, with linear-time backward passes.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com