Sign in

Repository Index

142,187 visible repositories in the index

Tags: LLM tools
Tags

A repository shows when it has any selected Tag.

Clear Tags
Filters (1)

Filters

Clear all filters

1–11 of 11 · Most stars

Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

  • cuda
  • flash-attention
  • fsdp
  • inference-engine