ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : Add Gemma 3 support (+ experimental vision capability) (#12343)

Browse source 
* llama : Add Gemma 3 text-only support

* fix python coding style

* fix compile on ubuntu

* python: fix style

* fix ubuntu compile

* fix build on ubuntu (again)

* fix ubuntu build, finally

* clip : Experimental support for Gemma 3 vision (#12344)

* clip : Experimental support for Gemma 3 vision

* fix build

* PRId64
This commit is contained in:
Xuan-Son Nguyen 2025-03-12 09:30:24 +01:00 • committed by GitHub
parent bf69cfe62f
commit 7841fc723e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 1202 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

19
gguf-py/gguf/constants.py
View file

@ -253,6 +253,7 @@ class MODEL_ARCH(IntEnum):
MINICPM3 = auto()
GEMMA = auto()
GEMMA2 = auto()
GEMMA3 = auto()
STARCODER2 = auto()
RWKV6 = auto()
RWKV6QWEN2 = auto()
@ -440,6 +441,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.MINICPM3: "minicpm3",
MODEL_ARCH.GEMMA: "gemma",
MODEL_ARCH.GEMMA2: "gemma2",
MODEL_ARCH.GEMMA3: "gemma3",
MODEL_ARCH.STARCODER2: "starcoder2",
MODEL_ARCH.RWKV6: "rwkv6",
MODEL_ARCH.RWKV6QWEN2: "rwkv6qwen2",
@ -1077,6 +1079,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_PRE_NORM,
MODEL_TENSOR.FFN_POST_NORM,
],
MODEL_ARCH.GEMMA3: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_PRE_NORM,
MODEL_TENSOR.FFN_POST_NORM,
],
MODEL_ARCH.STARCODER2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,