LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

mimo2: address MTP review feedback (#26228)

Browse Source 
Co-authored-by: tnhnyc <115956684+tnhnyc@users.noreply.github.com>
This commit is contained in:
Tunahan
2026-07-30 11:55:58 +08:00
committed by GitHub
co-authored by tnhnyc
parent 3018a11e79
commit 64d528be72
4 changed files with 191 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+3
View File
@@ -4440,8 +4440,11 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_EXP_PROBS_B,
MODEL_TENSOR.LAYER_OUT_NORM,
MODEL_TENSOR.NEXTN_EH_PROJ,
MODEL_TENSOR.NEXTN_EMBED_TOKENS,
MODEL_TENSOR.NEXTN_ENORM,
MODEL_TENSOR.NEXTN_HNORM,
MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD,
MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
],
MODEL_ARCH.STEP35: [
MODEL_TENSOR.TOKEN_EMBD,