From 9b61acf06041dcbaff6afa5f28940e93297f8520 Mon Sep 17 00:00:00 2001
From: Xuan-Son Nguyen <son@huggingface.co>
Date: Mon, 5 May 2025 16:02:55 +0200
Subject: [PATCH] mtmd : rename llava directory to mtmd (#13311)

* mv llava to mtmd

* change ref everywhere
---
 Makefile                                      |  38 +++++++++---------
 common/arg.cpp                                |   4 +-
 common/common.h                               |   2 +-
 docs/multimodal/MobileVLM.md                  |  12 +++---
 docs/multimodal/glmedge.md                    |   4 +-
 docs/multimodal/llava.md                      |  12 +++---
 docs/multimodal/minicpmo2.6.md                |   4 +-
 docs/multimodal/minicpmv2.5.md                |   4 +-
 docs/multimodal/minicpmv2.6.md                |   4 +-
 requirements/requirements-all.txt             |   2 +-
 tools/CMakeLists.txt                          |   2 +-
 tools/{llava => mtmd}/CMakeLists.txt          |   0
 tools/{llava => mtmd}/README-quantize.md      |   0
 tools/{llava => mtmd}/README.md               |   0
 tools/{llava => mtmd}/android/adb_run.sh      |   0
 tools/{llava => mtmd}/android/build_64.sh     |   0
 tools/{llava => mtmd}/clip-impl.h             |   0
 tools/{llava => mtmd}/clip-quantize-cli.cpp   |   0
 tools/{llava => mtmd}/clip.cpp                |   0
 tools/{llava => mtmd}/clip.h                  |   0
 .../convert_image_encoder_to_gguf.py          |   0
 tools/{llava => mtmd}/deprecation-warning.cpp |   0
 .../glmedge-convert-image-encoder-to-gguf.py  |   0
 tools/{llava => mtmd}/glmedge-surgery.py      |   0
 tools/{llava => mtmd}/llava.cpp               |   0
 tools/{llava => mtmd}/llava.h                 |   0
 tools/{llava => mtmd}/llava_surgery.py        |   0
 tools/{llava => mtmd}/llava_surgery_v2.py     |   0
 .../minicpmv-convert-image-encoder-to-gguf.py |   0
 tools/{llava => mtmd}/minicpmv-surgery.py     |   0
 tools/{llava => mtmd}/mtmd-cli.cpp            |   0
 tools/{llava => mtmd}/mtmd.cpp                |   0
 tools/{llava => mtmd}/mtmd.h                  |   0
 tools/{llava => mtmd}/qwen2vl-test.cpp        |   0
 tools/{llava => mtmd}/requirements.txt        |   0
 tools/{llava => mtmd}/test-1.jpeg             | Bin
 tools/{llava => mtmd}/tests.sh                |   0
 37 files changed, 44 insertions(+), 44 deletions(-)
 rename tools/{llava => mtmd}/CMakeLists.txt (100%)
 rename tools/{llava => mtmd}/README-quantize.md (100%)
 rename tools/{llava => mtmd}/README.md (100%)
 rename tools/{llava => mtmd}/android/adb_run.sh (100%)
 rename tools/{llava => mtmd}/android/build_64.sh (100%)
 rename tools/{llava => mtmd}/clip-impl.h (100%)
 rename tools/{llava => mtmd}/clip-quantize-cli.cpp (100%)
 rename tools/{llava => mtmd}/clip.cpp (100%)
 rename tools/{llava => mtmd}/clip.h (100%)
 rename tools/{llava => mtmd}/convert_image_encoder_to_gguf.py (100%)
 rename tools/{llava => mtmd}/deprecation-warning.cpp (100%)
 rename tools/{llava => mtmd}/glmedge-convert-image-encoder-to-gguf.py (100%)
 rename tools/{llava => mtmd}/glmedge-surgery.py (100%)
 rename tools/{llava => mtmd}/llava.cpp (100%)
 rename tools/{llava => mtmd}/llava.h (100%)
 rename tools/{llava => mtmd}/llava_surgery.py (100%)
 rename tools/{llava => mtmd}/llava_surgery_v2.py (100%)
 rename tools/{llava => mtmd}/minicpmv-convert-image-encoder-to-gguf.py (100%)
 rename tools/{llava => mtmd}/minicpmv-surgery.py (100%)
 rename tools/{llava => mtmd}/mtmd-cli.cpp (100%)
 rename tools/{llava => mtmd}/mtmd.cpp (100%)
 rename tools/{llava => mtmd}/mtmd.h (100%)
 rename tools/{llava => mtmd}/qwen2vl-test.cpp (100%)
 rename tools/{llava => mtmd}/requirements.txt (100%)
 rename tools/{llava => mtmd}/test-1.jpeg (100%)
 rename tools/{llava => mtmd}/tests.sh (100%)

diff --git a/Makefile b/Makefile
index 305037089..68b6fe59a 100644
--- a/Makefile
+++ b/Makefile
@@ -1394,36 +1394,36 @@ llama-gen-docs: examples/gen-docs/gen-docs.cpp \
 	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
-libllava.a: tools/llava/llava.cpp \
-	tools/llava/llava.h \
-	tools/llava/clip.cpp \
-	tools/llava/clip.h \
+libllava.a: tools/mtmd/llava.cpp \
+	tools/mtmd/llava.h \
+	tools/mtmd/clip.cpp \
+	tools/mtmd/clip.h \
 	common/stb_image.h \
 	common/base64.hpp \
 	$(OBJ_ALL)
 	$(CXX) $(CXXFLAGS) -static -fPIC -c $< -o $@ -Wno-cast-qual
 
-llama-llava-cli: tools/llava/llava-cli.cpp \
-	tools/llava/llava.cpp \
-	tools/llava/llava.h \
-	tools/llava/clip.cpp \
-	tools/llava/clip.h \
+llama-llava-cli: tools/mtmd/llava-cli.cpp \
+	tools/mtmd/llava.cpp \
+	tools/mtmd/llava.h \
+	tools/mtmd/clip.cpp \
+	tools/mtmd/clip.h \
 	$(OBJ_ALL)
 	$(CXX) $(CXXFLAGS) $< $(filter-out %.h $<,$^) -o $@ $(LDFLAGS) -Wno-cast-qual
 
-llama-minicpmv-cli: tools/llava/minicpmv-cli.cpp \
-	tools/llava/llava.cpp \
-	tools/llava/llava.h \
-	tools/llava/clip.cpp \
-	tools/llava/clip.h \
+llama-minicpmv-cli: tools/mtmd/minicpmv-cli.cpp \
+	tools/mtmd/llava.cpp \
+	tools/mtmd/llava.h \
+	tools/mtmd/clip.cpp \
+	tools/mtmd/clip.h \
 	$(OBJ_ALL)
 	$(CXX) $(CXXFLAGS) $< $(filter-out %.h $<,$^) -o $@ $(LDFLAGS) -Wno-cast-qual
 
-llama-qwen2vl-cli: tools/llava/qwen2vl-cli.cpp \
-	tools/llava/llava.cpp \
-	tools/llava/llava.h \
-	tools/llava/clip.cpp \
-	tools/llava/clip.h \
+llama-qwen2vl-cli: tools/mtmd/qwen2vl-cli.cpp \
+	tools/mtmd/llava.cpp \
+	tools/mtmd/llava.h \
+	tools/mtmd/clip.cpp \
+	tools/mtmd/clip.h \
 	$(OBJ_ALL)
 	$(CXX) $(CXXFLAGS) $< $(filter-out %.h $<,$^) -o $@ $(LDFLAGS) -Wno-cast-qual
 
diff --git a/common/arg.cpp b/common/arg.cpp
index 5080aa2fc..490991b23 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -2211,14 +2211,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
     add_opt(common_arg(
         {"--mmproj"}, "FILE",
-        "path to a multimodal projector file. see tools/llava/README.md",
+        "path to a multimodal projector file. see tools/mtmd/README.md",
         [](common_params & params, const std::string & value) {
             params.mmproj.path = value;
         }
     ).set_examples(mmproj_examples));
     add_opt(common_arg(
         {"--mmproj-url"}, "URL",
-        "URL to a multimodal projector file. see tools/llava/README.md",
+        "URL to a multimodal projector file. see tools/mtmd/README.md",
         [](common_params & params, const std::string & value) {
             params.mmproj.url = value;
         }
diff --git a/common/common.h b/common/common.h
index cfe1b7278..416939da9 100644
--- a/common/common.h
+++ b/common/common.h
@@ -340,7 +340,7 @@ struct common_params {
 
     common_conversation_mode conversation_mode = COMMON_CONVERSATION_MODE_AUTO;
 
-    // multimodal models (see tools/llava)
+    // multimodal models (see tools/mtmd)
     struct common_params_model mmproj;
     bool mmproj_use_gpu = true;     // use GPU for multimodal model
     bool no_mmproj = false;         // explicitly disable multimodal model
diff --git a/docs/multimodal/MobileVLM.md b/docs/multimodal/MobileVLM.md
index a647d7d35..4f5eca619 100644
--- a/docs/multimodal/MobileVLM.md
+++ b/docs/multimodal/MobileVLM.md
@@ -33,13 +33,13 @@ git clone https://huggingface.co/openai/clip-vit-large-patch14-336
 2. Use `llava_surgery.py` to split the LLaVA model to LLaMA and multimodel projector constituents:
 
 ```sh
-python ./tools/llava/llava_surgery.py -m path/to/MobileVLM-1.7B
+python ./tools/mtmd/llava_surgery.py -m path/to/MobileVLM-1.7B
 ```
 
 3. Use `convert_image_encoder_to_gguf.py` with `--projector-type ldp` (for **V2** please use `--projector-type ldpv2`) to convert the LLaVA image encoder to GGUF:
 
 ```sh
-python ./tools/llava/convert_image_encoder_to_gguf.py \
+python ./tools/mtmd/convert_image_encoder_to_gguf.py \
     -m path/to/clip-vit-large-patch14-336 \
     --llava-projector path/to/MobileVLM-1.7B/llava.projector \
     --output-dir path/to/MobileVLM-1.7B \
@@ -47,7 +47,7 @@ python ./tools/llava/convert_image_encoder_to_gguf.py \
 ```
 
 ```sh
-python ./tools/llava/convert_image_encoder_to_gguf.py \
+python ./tools/mtmd/convert_image_encoder_to_gguf.py \
     -m path/to/clip-vit-large-patch14-336 \
     --llava-projector path/to/MobileVLM-1.7B_V2/llava.projector \
     --output-dir path/to/MobileVLM-1.7B_V2 \
@@ -69,10 +69,10 @@ Now both the LLaMA part and the image encoder is in the `MobileVLM-1.7B` directo
 
 ## Android compile and run
 ### compile
-refer to `tools/llava/android/build_64.sh`
+refer to `tools/mtmd/android/build_64.sh`
 ```sh
-mkdir tools/llava/android/build_64
-cd tools/llava/android/build_64
+mkdir tools/mtmd/android/build_64
+cd tools/mtmd/android/build_64
 ../build_64.sh
 ```
 ### run on Android
diff --git a/docs/multimodal/glmedge.md b/docs/multimodal/glmedge.md
index e7dfafdde..7bae83150 100644
--- a/docs/multimodal/glmedge.md
+++ b/docs/multimodal/glmedge.md
@@ -25,13 +25,13 @@ git clone https://huggingface.co/THUDM/glm-edge-v-5b or https://huggingface.co/T
 2. Use `glmedge-surgery.py` to split the GLMV-EDGE model to LLM and multimodel projector constituents:
 
 ```sh
-python ./tools/llava/glmedge-surgery.py -m ../model_path
+python ./tools/mtmd/glmedge-surgery.py -m ../model_path
 ```
 
 4. Use `glmedge-convert-image-encoder-to-gguf.py` to convert the GLMV-EDGE image encoder to GGUF:
 
 ```sh
-python ./tools/llava/glmedge-convert-image-encoder-to-gguf.py -m ../model_path --llava-projector ../model_path/glm.projector --output-dir ../model_path
+python ./tools/mtmd/glmedge-convert-image-encoder-to-gguf.py -m ../model_path --llava-projector ../model_path/glm.projector --output-dir ../model_path
 ```
 
 5. Use `examples/convert_hf_to_gguf.py` to convert the LLM part of GLMV-EDGE to GGUF:
diff --git a/docs/multimodal/llava.md b/docs/multimodal/llava.md
index 0087b1061..12354ab60 100644
--- a/docs/multimodal/llava.md
+++ b/docs/multimodal/llava.md
@@ -37,19 +37,19 @@ git clone https://huggingface.co/openai/clip-vit-large-patch14-336
 2. Install the required Python packages:
 
 ```sh
-pip install -r tools/llava/requirements.txt
+pip install -r tools/mtmd/requirements.txt
 ```
 
 3. Use `llava_surgery.py` to split the LLaVA model to LLaMA and multimodel projector constituents:
 
 ```sh
-python ./tools/llava/llava_surgery.py -m ../llava-v1.5-7b
+python ./tools/mtmd/llava_surgery.py -m ../llava-v1.5-7b
 ```
 
 4. Use `convert_image_encoder_to_gguf.py` to convert the LLaVA image encoder to GGUF:
 
 ```sh
-python ./tools/llava/convert_image_encoder_to_gguf.py -m ../clip-vit-large-patch14-336 --llava-projector ../llava-v1.5-7b/llava.projector --output-dir ../llava-v1.5-7b
+python ./tools/mtmd/convert_image_encoder_to_gguf.py -m ../clip-vit-large-patch14-336 --llava-projector ../llava-v1.5-7b/llava.projector --output-dir ../llava-v1.5-7b
 ```
 
 5. Use `examples/convert_legacy_llama.py` to convert the LLaMA part of LLaVA to GGUF:
@@ -69,12 +69,12 @@ git clone https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b
 2) Install the required Python packages:
 
 ```sh
-pip install -r tools/llava/requirements.txt
+pip install -r tools/mtmd/requirements.txt
 ```
 
 3) Use `llava_surgery_v2.py` which also supports llava-1.5 variants pytorch as well as safetensor models:
 ```console
-python tools/llava/llava_surgery_v2.py -C -m ../llava-v1.6-vicuna-7b/
+python tools/mtmd/llava_surgery_v2.py -C -m ../llava-v1.6-vicuna-7b/
 ```
 - you will find a llava.projector and a llava.clip file in your model directory
 
@@ -88,7 +88,7 @@ curl -s -q https://huggingface.co/cmp-nct/llava-1.6-gguf/raw/main/config_vit.jso
 
 5) Create the visual gguf model:
 ```console
-python ./tools/llava/convert_image_encoder_to_gguf.py -m vit --llava-projector vit/llava.projector --output-dir vit --clip-model-is-vision
+python ./tools/mtmd/convert_image_encoder_to_gguf.py -m vit --llava-projector vit/llava.projector --output-dir vit --clip-model-is-vision
 ```
 - This is similar to llava-1.5, the difference is that we tell the encoder that we are working with the pure vision model part of CLIP
 
diff --git a/docs/multimodal/minicpmo2.6.md b/docs/multimodal/minicpmo2.6.md
index c9aab8abc..8c6db8efe 100644
--- a/docs/multimodal/minicpmo2.6.md
+++ b/docs/multimodal/minicpmo2.6.md
@@ -29,8 +29,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf) by us)
 
 ```bash
-python ./tools/llava/minicpmv-surgery.py -m ../MiniCPM-o-2_6
-python ./tools/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-o-2_6 --minicpmv-projector ../MiniCPM-o-2_6/minicpmv.projector --output-dir ../MiniCPM-o-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 4
+python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-o-2_6
+python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-o-2_6 --minicpmv-projector ../MiniCPM-o-2_6/minicpmv.projector --output-dir ../MiniCPM-o-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 4
 python ./convert_hf_to_gguf.py ../MiniCPM-o-2_6/model
 
 # quantize int4 version
diff --git a/docs/multimodal/minicpmv2.5.md b/docs/multimodal/minicpmv2.5.md
index 4603bd7c1..19b439607 100644
--- a/docs/multimodal/minicpmv2.5.md
+++ b/docs/multimodal/minicpmv2.5.md
@@ -28,8 +28,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf) by us)
 
 ```bash
-python ./tools/llava/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
-python ./tools/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
+python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
+python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
 python ./convert_hf_to_gguf.py ../MiniCPM-Llama3-V-2_5/model
 
 # quantize int4 version
diff --git a/docs/multimodal/minicpmv2.6.md b/docs/multimodal/minicpmv2.6.md
index 69ebc1296..15c1bbd12 100644
--- a/docs/multimodal/minicpmv2.6.md
+++ b/docs/multimodal/minicpmv2.6.md
@@ -28,8 +28,8 @@ cmake --build build --config Release
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-V-2_6-gguf) by us)
 
 ```bash
-python ./tools/llava/minicpmv-surgery.py -m ../MiniCPM-V-2_6
-python ./tools/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-V-2_6 --minicpmv-projector ../MiniCPM-V-2_6/minicpmv.projector --output-dir ../MiniCPM-V-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 3
+python ./tools/mtmd/minicpmv-surgery.py -m ../MiniCPM-V-2_6
+python ./tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-V-2_6 --minicpmv-projector ../MiniCPM-V-2_6/minicpmv.projector --output-dir ../MiniCPM-V-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 3
 python ./convert_hf_to_gguf.py ../MiniCPM-V-2_6/model
 
 # quantize int4 version
diff --git a/requirements/requirements-all.txt b/requirements/requirements-all.txt
index 4b6d4b7d7..9fa7d4d0a 100644
--- a/requirements/requirements-all.txt
+++ b/requirements/requirements-all.txt
@@ -1,4 +1,4 @@
--r ../tools/llava/requirements.txt
+-r ../tools/mtmd/requirements.txt
 -r ../tools/server/bench/requirements.txt
 -r ../tools/server/tests/requirements.txt
 
diff --git a/tools/CMakeLists.txt b/tools/CMakeLists.txt
index 06a96af55..d64956b84 100644
--- a/tools/CMakeLists.txt
+++ b/tools/CMakeLists.txt
@@ -27,7 +27,7 @@ else()
     add_subdirectory(run)
     add_subdirectory(tokenize)
     add_subdirectory(tts)
-    add_subdirectory(llava)
+    add_subdirectory(mtmd)
     if (GGML_RPC)
         add_subdirectory(rpc)
     endif()
diff --git a/tools/llava/CMakeLists.txt b/tools/mtmd/CMakeLists.txt
similarity index 100%
rename from tools/llava/CMakeLists.txt
rename to tools/mtmd/CMakeLists.txt
diff --git a/tools/llava/README-quantize.md b/tools/mtmd/README-quantize.md
similarity index 100%
rename from tools/llava/README-quantize.md
rename to tools/mtmd/README-quantize.md
diff --git a/tools/llava/README.md b/tools/mtmd/README.md
similarity index 100%
rename from tools/llava/README.md
rename to tools/mtmd/README.md
diff --git a/tools/llava/android/adb_run.sh b/tools/mtmd/android/adb_run.sh
similarity index 100%
rename from tools/llava/android/adb_run.sh
rename to tools/mtmd/android/adb_run.sh
diff --git a/tools/llava/android/build_64.sh b/tools/mtmd/android/build_64.sh
similarity index 100%
rename from tools/llava/android/build_64.sh
rename to tools/mtmd/android/build_64.sh
diff --git a/tools/llava/clip-impl.h b/tools/mtmd/clip-impl.h
similarity index 100%
rename from tools/llava/clip-impl.h
rename to tools/mtmd/clip-impl.h
diff --git a/tools/llava/clip-quantize-cli.cpp b/tools/mtmd/clip-quantize-cli.cpp
similarity index 100%
rename from tools/llava/clip-quantize-cli.cpp
rename to tools/mtmd/clip-quantize-cli.cpp
diff --git a/tools/llava/clip.cpp b/tools/mtmd/clip.cpp
similarity index 100%
rename from tools/llava/clip.cpp
rename to tools/mtmd/clip.cpp
diff --git a/tools/llava/clip.h b/tools/mtmd/clip.h
similarity index 100%
rename from tools/llava/clip.h
rename to tools/mtmd/clip.h
diff --git a/tools/llava/convert_image_encoder_to_gguf.py b/tools/mtmd/convert_image_encoder_to_gguf.py
similarity index 100%
rename from tools/llava/convert_image_encoder_to_gguf.py
rename to tools/mtmd/convert_image_encoder_to_gguf.py
diff --git a/tools/llava/deprecation-warning.cpp b/tools/mtmd/deprecation-warning.cpp
similarity index 100%
rename from tools/llava/deprecation-warning.cpp
rename to tools/mtmd/deprecation-warning.cpp
diff --git a/tools/llava/glmedge-convert-image-encoder-to-gguf.py b/tools/mtmd/glmedge-convert-image-encoder-to-gguf.py
similarity index 100%
rename from tools/llava/glmedge-convert-image-encoder-to-gguf.py
rename to tools/mtmd/glmedge-convert-image-encoder-to-gguf.py
diff --git a/tools/llava/glmedge-surgery.py b/tools/mtmd/glmedge-surgery.py
similarity index 100%
rename from tools/llava/glmedge-surgery.py
rename to tools/mtmd/glmedge-surgery.py
diff --git a/tools/llava/llava.cpp b/tools/mtmd/llava.cpp
similarity index 100%
rename from tools/llava/llava.cpp
rename to tools/mtmd/llava.cpp
diff --git a/tools/llava/llava.h b/tools/mtmd/llava.h
similarity index 100%
rename from tools/llava/llava.h
rename to tools/mtmd/llava.h
diff --git a/tools/llava/llava_surgery.py b/tools/mtmd/llava_surgery.py
similarity index 100%
rename from tools/llava/llava_surgery.py
rename to tools/mtmd/llava_surgery.py
diff --git a/tools/llava/llava_surgery_v2.py b/tools/mtmd/llava_surgery_v2.py
similarity index 100%
rename from tools/llava/llava_surgery_v2.py
rename to tools/mtmd/llava_surgery_v2.py
diff --git a/tools/llava/minicpmv-convert-image-encoder-to-gguf.py b/tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py
similarity index 100%
rename from tools/llava/minicpmv-convert-image-encoder-to-gguf.py
rename to tools/mtmd/minicpmv-convert-image-encoder-to-gguf.py
diff --git a/tools/llava/minicpmv-surgery.py b/tools/mtmd/minicpmv-surgery.py
similarity index 100%
rename from tools/llava/minicpmv-surgery.py
rename to tools/mtmd/minicpmv-surgery.py
diff --git a/tools/llava/mtmd-cli.cpp b/tools/mtmd/mtmd-cli.cpp
similarity index 100%
rename from tools/llava/mtmd-cli.cpp
rename to tools/mtmd/mtmd-cli.cpp
diff --git a/tools/llava/mtmd.cpp b/tools/mtmd/mtmd.cpp
similarity index 100%
rename from tools/llava/mtmd.cpp
rename to tools/mtmd/mtmd.cpp
diff --git a/tools/llava/mtmd.h b/tools/mtmd/mtmd.h
similarity index 100%
rename from tools/llava/mtmd.h
rename to tools/mtmd/mtmd.h
diff --git a/tools/llava/qwen2vl-test.cpp b/tools/mtmd/qwen2vl-test.cpp
similarity index 100%
rename from tools/llava/qwen2vl-test.cpp
rename to tools/mtmd/qwen2vl-test.cpp
diff --git a/tools/llava/requirements.txt b/tools/mtmd/requirements.txt
similarity index 100%
rename from tools/llava/requirements.txt
rename to tools/mtmd/requirements.txt
diff --git a/tools/llava/test-1.jpeg b/tools/mtmd/test-1.jpeg
similarity index 100%
rename from tools/llava/test-1.jpeg
rename to tools/mtmd/test-1.jpeg
diff --git a/tools/llava/tests.sh b/tools/mtmd/tests.sh
similarity index 100%
rename from tools/llava/tests.sh
rename to tools/mtmd/tests.sh