Ettore Di Giacinto fbc93b0a34 fix(llama-cpp): default rms_norm_eps for Gemma 3 GGUFs missing the key ...

Some Gemma 3 GGUF files distributed via the Ollama registry omit the
`gemma3.attention.layer_norm_rms_epsilon` metadata key. Both llama.cpp
and ik_llama.cpp treat that key as required and abort the load with:

    error loading model hyperparameters:
    key not found in model: gemma3.attention.layer_norm_rms_epsilon

Ollama's loader silently falls back to ~1e-6 in the same situation,
which is the canonical Gemma 3 default (google/gemma_pytorch config.py
and the Hugging Face Gemma3Config), and the model loads correctly.

Add small build-time patches to both backends that pre-seed
`hparams.f_norm_rms_eps` with 1e-6 and mark the metadata lookup as
optional. GGUFs that already carry the key continue to use the embedded
value unchanged.

Closes #9414

2026-04-19 16:15:26 +00:00

..

grpc

fix: speedup git submodule update with --single-branch (#2847)

2024-07-13 22:32:25 +02:00

ik-llama-cpp

fix(llama-cpp): default rms_norm_eps for Gemma 3 GGUFs missing the key

2026-04-19 16:15:26 +00:00

llama-cpp

fix(llama-cpp): default rms_norm_eps for Gemma 3 GGUFs missing the key

2026-04-19 16:15:26 +00:00

turboquant

chore: ⬆️ Update TheTom/llama-cpp-turboquant to `45f8a066ed5f5bb38c695cec532f6cef9f4efa9d' (#9385)

2026-04-17 08:12:21 +02:00