Skip to content

Gemma3 NF4 on GPU: quantized encoder, batch encoding, byte-LUT eager dequant - #39

Merged
TroyHernandez merged 5 commits into
mainfrom
perf/gemma3-gpu-nf4
Jul 21, 2026
Merged

Gemma3 NF4 on GPU: quantized encoder, batch encoding, byte-LUT eager dequant#39
TroyHernandez merged 5 commits into
mainfrom
perf/gemma3-gpu-nf4

gemma3_encode_batch: sub-batched prompt encoding with disk cache

deceec5
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
ci (ubuntu-latest)
succeeded Jul 21, 2026 in 3m 26s