pali112
/
ollama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,431 Commits 315 Branches 369 Tags 262 MiB
Commit Graph

3 Commits

Author SHA1 Message Date
Oliver Simons 1ee3fe46f3
Increase performance for Gemma3n models on NVGPUs by enabling CUDA Graph execution (#11525) 
* Enable CUDA Graphs for gemma3n.

Similar to
https://github.com/ggml-org/llama.cpp/pull/14741,
though ollama has a slightly different model graph
than llama.cpp which requires different workaround
checks.

* Remove residual check by reshaping differently in gemma3n model

This should make the heuristics more robust
 2025-12-29 06:39:47 -06:00
Michael Yang 1cdab47113
chore: cleanup comments + unused vars (#11225) 2025-12-29 06:39:39 -06:00
Michael Yang 801564fa8b
add new gemma model (#11204) 
* update patches

* cherry pick metal mean kernel

* cherry pick cuda mean kernel

* gemma3n
 2025-12-29 06:39:38 -06:00