upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-21 05:27:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

convert: enable --fuse-qkv for muse-glimmer (#29203)

Browse Source
This commit is contained in:
David Friehs
2026-09-21 10:38:28 +03:00
committed by GitHub
parent ce8caa6e60
commit 62668d6b26
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+1
View File
@@ -3709,6 +3709,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,