Open source

ggml-org/llama.cpp b10615

GitHub Releases · github-actions[bot] · 24 days ago

<details open> metal : per-device tuned (Q, NE) for flash-attn vec (#26570) * metal : per-device tuned (Q, NE) for flash-attn vec (#25750) * rebase Q-generic FA vec body from 01dc93607 (#23114) * add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133) * add FA vec (Q,NE)…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 589.0 h
Stored score: 0.00002
Current score: 0.00002
First seen: 2026-08-25T08:37:05.923Z

Newsletter

Get practical AI engineering notes

Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.