X · @teortaxesTex
· X / Twitter
RT Larry Dial: Question for the LLM Research Community: Is anyone aware of fully reproducible experimental results showing that MLA beats GQA under th…
RT Larry DialQuestion for the LLM Research Community: Is anyone aware of fully reproducible experimental results showing that MLA beats GQA under the same KV cache? I ask for two reasons: (1) I find it surprising that there is still a divide between Chinese labs using MLA, and Western labs using GQA + sliding window, w