CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

support qwen3vl series.

Browse Source 
Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>
This commit is contained in:
JJJYmmm
2025-10-26 19:18:15 +08:00
parent 5d195f17bc
commit 1e4fd19446
17 changed files with 1019 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
gguf-py/gguf/tensor_mapping.py
View File

@@ -1185,6 +1185,7 @@ class TensorNameMap:
"model.vision_model.embeddings.position_embedding", # SmolVLM
"vision_model.positional_embedding_vlm", # llama 4
"vision_tower.patch_embed.pos_emb", # kimi-vl
"visual.pos_embed", # qwen3vl
),
MODEL_TENSOR.V_ENC_ATTN_Q: (
@@ -1282,6 +1283,7 @@ class TensorNameMap:
"vision_model.model.layers.{bid}.mlp.fc1", # llama4
"visual.blocks.{bid}.mlp.fc1", # qwen2vl
"visual.blocks.{bid}.mlp.up_proj", # qwen2.5vl
"visual.blocks.{bid}.mlp.linear_fc1", # qwen3vl
"vision_tower.encoder.blocks.{bid}.mlp.fc0", # kimi-vl (fc0/fc1)
),
@@ -1301,6 +1303,7 @@ class TensorNameMap:
"vision_model.model.layers.{bid}.mlp.fc2", # llama4
"visual.blocks.{bid}.mlp.fc2", # qwen2vl
"visual.blocks.{bid}.mlp.down_proj", # qwen2.5vl
"visual.blocks.{bid}.mlp.linear_fc2", # qwen3vl
"vision_tower.encoder.blocks.{bid}.mlp.fc1", # kimi-vl (fc0/fc1)
),
@@ -1397,6 +1400,18 @@ class TensorNameMap:
"patch_merger.merging_layer", # mistral
),
MODEL_TENSOR.V_DS_NORM: (
"model.visual.deepstack_merger_list.{bid}.norm", # deepstack in qwen3vl
),
MODEL_TENSOR.V_DS_FC1: (
"model.visual.deepstack_merger_list.{bid}.linear_fc1", # deepstack in qwen3vl
),
MODEL_TENSOR.V_DS_FC2: (
"model.visual.deepstack_merger_list.{bid}.linear_fc2", # deepstack in qwen3vl
),
# audio (mtmd)
MODEL_TENSOR.A_ENC_EMBD_POS: (