nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

model : support Gemma4_26B_A4B_NVFP4 (#22804)

Browse Source 
* Gemma4_26B_A4B_NvFp4 hf checkpoint convert to gguf format fixes

Signed-off-by: ynankani <ynankani@nvidia.com>

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Address review comments

Signed-off-by: ynankani <ynankani@nvidia.com>

* fix CRLF

Signed-off-by: ynankani <ynankani@nvidia.com>

* Lint error fix

Signed-off-by: ynankani <ynankani@nvidia.com>

---------

Signed-off-by: ynankani <ynankani@nvidia.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
ynankani
2026-05-08 18:42:09 +00:00
committed by GitHub
parent f9cd456ea5
commit 9f5f0e689c
3 changed files with 38 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/constants.py
View File

@@ -2443,6 +2443,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_GATE_UP_EXP,
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_UP_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_POST_NORM,