CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-09 10:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/imatrix-batched-chunks

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-02-09 12:06:24 -05:00
parent db502ddd0e 19d3c8293b
commit 1be357d990
149 changed files with 14407 additions and 5105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
gguf-py/gguf/constants.py
View File

@@ -1364,6 +1364,9 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,