Update MiniCPM-V-4 model to be compatible with LiteRT-LM runtime at HEAD

MiniCPM-V-4-int8.litertlm

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae545078bdada2752a92eadd41a33d8ce86848b42faf9acb30bdaaaba8676a17
+oid sha256:d45ef0cd8141597d731d002b72a152ab1a0f8b9cda8d9a0f5e1bc3a4689dcbd0
 size 4214021104

README.md

@@ -56,16 +56,48 @@ Full MME evaluation running the INT8 bundle on-device:
 
 ## Usage
 
-Run with a LiteRT-LM CPU runner:
+### Run with `litert_lm_advanced_main`
+
+You can run multimodal inference using `litert_lm_advanced_main` from the [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) repository. `litert_lm_advanced_main` supports inline media markers (such as `[image:/path/to/image.png]`) within `--input_prompt`.
+
+#### 1. Build the Runner
+
+From the LiteRT-LM repository:
+
+```bash
+bazel build -c opt //runtime/engine:litert_lm_advanced_main
+```
+
+#### 2. Run Inference
+
+Using `bazel run`:
 
 ```bash
-LD_LIBRARY_PATH=. ./litert_lm_main \
-  --model_path=./MiniCPM-V-4-int8.litertlm \
+bazel run -c opt //runtime/engine:litert_lm_advanced_main -- \
   --backend=cpu \
-  --image_path=./image.jpg \
-  --input_prompt="What is in this image?"
+  --vision_backend=cpu \
+  --model_path=/path/to/MiniCPM-V-4-int8.litertlm \
+  --input_prompt="What is in this image? [image:/path/to/image.png]"
 ```
 
+Or execute the compiled binary directly:
+
+```bash
+./bazel-bin/runtime/engine/litert_lm_advanced_main \
+  --backend=cpu \
+  --vision_backend=cpu \
+  --model_path=/path/to/MiniCPM-V-4-int8.litertlm \
+  --input_prompt="What is in this image? [image:/path/to/image.png]"
+```
+
+#### Key Options
+
+- `--backend=cpu`: Runs LLM prefill and decode on CPU.
+- `--vision_backend=cpu`: Enables the vision modality and runs the SigLIP vision encoder on CPU.
+- `--input_prompt`: Prompt text including image path using `[image:/path/to/image.png]`.
+- `--max_output_tokens`: (Optional) Limit the maximum number of generated tokens (e.g. `--max_output_tokens=128`).
+- `--min_log_severity=2`: (Optional) Display info logs, such as vision executor properties (`num_tokens_per_image: 64`, `patch_num_shrink_factor: 17`).
+
 ## License
 
 Follows the license of the base model — see **https://huggingface.co/openbmb/MiniCPM-V-4**.