]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 4eb1951)
gguf-py : fix missing comma after bad merge in tensor-mapping (#21558)
authorDaniel Bevenius <redacted>
Tue, 7 Apr 2026 19:24:25 +0000 (21:24 +0200)
committerGitHub <redacted>
Tue, 7 Apr 2026 19:24:25 +0000 (21:24 +0200)
commit93bdc6156333082421d82b52d36f7dacb0542495
treebd58b1baa7a4ae6de95290deaa6284b602505fb0tree
parent4eb19514dd2984662f13aacbb052c559c8fde3b1commit | diff
gguf-py : fix missing comma after bad merge in tensor-mapping (#21558)

This commit adds a missing comma in the vision encoder attention qkv
block.

The motivation for this change is that without the comma there will be
a string concatenation of the Kimi-K2.5 and the Nemotron Nano v2 VL
tensor mappings which will be broken.
gguf-py/gguf/tensor_mapping.py diff | blob | history
Packaging of ggml-org/llama.cpp