?

https://dejan.ai/blog/turboquant-triton-kernel

https://dejan.ai/blog/turboquant-triton-kernel ↗
other 2 total activities
Activity Summary
1 success
Consensus Experiments (1)
Project Experiment Result Confidence Repro
TurboQuant KV Cache Optimization Dejan AI Triton kernel — MSE-only 2-bit (RTX 4090)
MSE-only approach (no QJL) at 2-bit produces character-identical output to fp16
success
0.14
1/5
All Completed Experiments (1)
Project Fork Experiment Result Date
TurboQuant KV Cache Optimization apple-silicon-baselines dejanseo
Dejan AI Triton kernel — MSE-only 2-bit (RTX 4090)
Independently validates MSE-only approach (no QJL residual correction) as superior. 2-bit character-identical to fp16 on Gemma 3 4B. We dropped QJL for the same reason. Code reviewed.
success 2026-03-25T00:00:00Z
Projects Tracking This Resource
No projects are tracking this resource.