happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

gguf-py : removed obsolete KV_B tensor from DEEPSEEK32 arch

This commit is contained in:
Stanisław Szymczyk 2026-03-24 21:28:28 +01:00
parent 0ee5d80ed3
commit 7f5578fe08
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
gguf-py/gguf/constants.py
View File

@ -2635,7 +2635,6 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ATTN_Q_A,
MODEL_TENSOR.ATTN_Q_B,
MODEL_TENSOR.ATTN_KV_A_MQA,
MODEL_TENSOR.ATTN_KV_B,
MODEL_TENSOR.ATTN_K_B,
MODEL_TENSOR.ATTN_V_B,
MODEL_TENSOR.ATTN_Q_A_NORM,