Tom Turney
@thetom
Working on LLM inference systems, KV cache compression, and kernel-level optimizations (TurboQuant).
3
Published Tools
7,296
Total Stars
0
Weekly Downloads
603
GitHub Followers
49
Public Repos
Published Tools
3 Skillsacross 2 categoriesTom Turney (TheTom)
REFRACT — Reference-anchored Robust Acid-test for Compressed Transformers. Multi-axis KV-cache fidelity scoring for LLMs across llama.cpp, MLX, vLLM, and SGLang.
...moreSkillai-ml
7K1 dir
Tom Turney (TheTom)
vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon
Skilluncategorised
2741 dir
TheTom
Unified toolkit for benchmarking and integrating TurboQuant+ KV-cache compression across inference engines (llama.cpp, vLLM, MLX).
...moreSkillai-ml
11 dir