zengxiao-he/tessera

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.

↗ Open on GitHub

Stars

566

Forks

Language

Python

License

NOASSERTION

Last push

3 months ago

Python rust llm cuda pytorch jax quantization knowledge-distillation triton inference-engine fsdp kv-cache flash-attention mechanistic-interpretability ml-systems paged-attention speculative-decoding

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.

Related intel (0)

No related intel yet