Open source / #4091
Open source
ggml-org/llama.cpp b10427
GitHub Releases · github-actions[bot] · 1 month ago
<details open> sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779) Measured on Arc Pro B70 (Battlemage, Level Zero), llama-bench -r 20, two interleaved rounds, tg128: qwen2.5-3B-Instruct Q4_K_M 154.18 -> 158.53 t/s +2.8% gemma-2-2b-it Q4_K_M 162.45 -> 165.62…
Source and ranking details
- Source adapter
- github-releases
- Source weight
- 3
- Points
- 0
- Age
- 842.7 h
- Stored score
- 0.00001
- Current score
- 0.00001
- First seen
- 2026-08-14T08:37:30.885Z
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.