Kawrakow d5507e33ae

Split mode graph for dense Gemma4 assistant (#2022) ...

* WIP: Split mode graph for Gemma4 assistant

Something is not right - acceptance drops to nearly zero.

* Per model CUDA contexts

Still not working!?

* This works

The issue was that I was not correctly calculating the number
of KV heads for the split KV cache.

* Compiler warnings

* It is better to use llama_context pointers as keys

2026-06-24 18:29:32 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Split mode graph for dense Gemma4 assistant (#2022)

2026-06-24 18:29:32 +02:00

src

Split mode graph for dense Gemma4 assistant (#2022)

2026-06-24 18:29:32 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

cmake: drop ggml-blas.h from GGML_PUBLIC_HEADERS (#2007)

2026-06-21 07:49:09 +02:00