diff --git a/docs/en/get_started/ascend/get_started.md b/docs/en/get_started/ascend/get_started.md
index 262381cadd..376548b0dc 100644
--- a/docs/en/get_started/ascend/get_started.md
+++ b/docs/en/get_started/ascend/get_started.md
@@ -1,72 +1,35 @@
-# Get Started with Huawei Ascend (Atlas 800T A2 & Atlas 300I Duo)
+# Get Started with Huawei Ascend
 
+We currently support running lmdeploy on **Atlas 800T A3, Atlas 800T A2 and Atlas 300I Duo**.
 The usage of lmdeploy on a Huawei Ascend device is almost the same as its usage on CUDA with PytorchEngine in lmdeploy.
 Please read the original [Get Started](../get_started.md) guide before reading this tutorial.
 
-Here is the [supported model list](../../supported_models/supported_models.md#PyTorchEngine-on-Huawei-Ascend-Platform).
+Here is the [supported model list](../../supported_models/supported_models.md#PyTorchEngine-on-Other-Platforms).
 
 > \[!IMPORTANT\]
-> We have uploaded a docker image with KUNPENG CPU to aliyun(from lmdeploy 0.7.1 + dlinfer 0.1.6).
+> We have uploaded a docker image with KUNPENG CPU to aliyun.
 > Please try to pull the image by following command:
+>
+> Atlas 800T A3:
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a3-latest`
+>
+> (Atlas 800T A3 currently supports only the Qwen-series with eager mode.)
+>
 > Atlas 800T A2:
-> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:910b-latest`
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest`
+>
 > 300I Duo:
-> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:310p-latest`
-> The dockerfile described below still works, you can try
-> both pulling image and build your own image by dockerfile.
-
-## Installation
-
-We highly recommend that users build a Docker image for streamlined environment setup.
-
-Git clone the source code of lmdeploy and the Dockerfile locates in the `docker` directory:
-
-```shell
-git clone https://github.com/InternLM/lmdeploy.git
-cd lmdeploy
-```
-
-### Environment Preparation
-
-The Docker version is supposed to be no less than `18.09`. And `Ascend Docker Runtime` should be installed by following [the official guide](https://www.hiascend.com/document/detail/zh/mindx-dl/600/clusterscheduling/clusterschedulingig/.clusterschedulingig/dlug_installation_012.html).
-
-> \[!CAUTION\]
-> If error message `libascend_hal.so: cannot open shared object file` shows, that means **Ascend Docker Runtime** is not installed correctly!
-
-#### Ascend Drivers, Firmware and CANN
-
-The target machine needs to install the Huawei driver and firmware version not lower than 23.0.3, refer to
-[CANN Driver and Firmware Installation](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha001/softwareinst/instg/instg_0005.html)
-and [download resources](https://www.hiascend.com/hardware/firmware-drivers/community?product=4&model=26&cann=8.0.RC2.beta1&driver=1.0.25.alpha).
-
-And the CANN (version 8.0.RC2.beta1) software packages should also be downloaded from [Ascend Resource Download Center](https://www.hiascend.com/developer/download/community/result?module=cann&cann=8.0.RC2.beta1&product=4&model=26) themselves. Make sure to place the `Ascend-cann-kernels-910b*.run`, `Ascend-cann-nnal_*.run` and `Ascend-cann-toolkit*-aarch64.run` under the root directory of lmdeploy source code
-
-#### Build Docker Image
-
-Run the following command in the root directory of lmdeploy to build the image:
-
-```bash
-DOCKER_BUILDKIT=1 docker build -t lmdeploy-aarch64-ascend:latest \
-    -f docker/Dockerfile_aarch64_ascend .
-```
-
-The `Dockerfile_aarch64_ascend` is tested on Kunpeng CPU. For intel CPU, please try [this dockerfile](https://github.com/InternLM/lmdeploy/issues/2745#issuecomment-2473285703) (which is not fully tested)
-
-If the following command executes without any errors, it indicates that the environment setup is successful.
-
-```bash
-docker run -e ASCEND_VISIBLE_DEVICES=0 --rm --name lmdeploy -t lmdeploy-aarch64-ascend:latest lmdeploy check_env
-```
-
-For more information about running the Docker client on Ascend devices, please refer to the [guide](https://www.hiascend.com/document/detail/zh/mindx-dl/600/clusterscheduling/dockerruntimeug/dlruntime_ug_013.html)
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:300i-duo-latest`
+>
+> (Atlas 300I Duo currently works only with graph mode.)
+>
+> To build the environment yourself, refer to the Dockerfiles [here](../../../../docker).
 
 ## Offline batch inference
 
-> \[!TIP\]
-> Graph mode has been supported on Atlas 800T A2.
-> Users can set `eager_mode=False` to enable graph mode, or, set `eager_mode=True` to disable graph mode.
-> (Please source `/usr/local/Ascend/nnal/atb/set_env.sh` before enabling graph mode)
-
 ### LLM inference
 
 Set `device_type="ascend"` in the `PytorchEngineConfig`:
@@ -74,12 +37,11 @@ Set `device_type="ascend"` in the `PytorchEngineConfig`:
 ```python
 from lmdeploy import pipeline
 from lmdeploy import PytorchEngineConfig
-if __name__ == "__main__":
-    pipe = pipeline("internlm/internlm2_5-7b-chat",
-                    backend_config=PytorchEngineConfig(tp=1, device_type="ascend", eager_mode=True))
-    question = ["Shanghai is", "Please introduce China", "How are you?"]
-    response = pipe(question)
-    print(response)
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+        backend_config=PytorchEngineConfig(tp=1, device_type="ascend"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
 ```
 
 ### VLM inference
@@ -89,34 +51,28 @@ Set `device_type="ascend"` in the `PytorchEngineConfig`:
 ```python
 from lmdeploy import pipeline, PytorchEngineConfig
 from lmdeploy.vl import load_image
-if __name__ == "__main__":
-    pipe = pipeline('OpenGVLab/InternVL2-2B',
-                    backend_config=PytorchEngineConfig(tp=1, device_type='ascend', eager_mode=True))
-    image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-    response = pipe(('describe this image', image))
-    print(response)
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+        backend_config=PytorchEngineConfig(tp=1, device_type='ascend'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
 ```
 
 ## Online serving
 
-> \[!TIP\]
-> Graph mode has been supported on Atlas 800T A2.
-> Graph mode is default enabled in online serving. Users can add `--eager-mode` to disable graph mode.
-> (Please source `/usr/local/Ascend/nnal/atb/set_env.sh` before enabling graph mode)
-
 ### Serve a LLM model
 
 Add `--device ascend` in the serve command.
 
 ```bash
-lmdeploy serve api_server --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat
+lmdeploy serve api_server --backend pytorch --device ascend internlm/internlm2_5-7b-chat
 ```
 
 Run the following commands to launch docker container for lmdeploy LLM serving:
 
 ```bash
-docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat"
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend internlm/internlm2_5-7b-chat"
 ```
 
 ### Serve a VLM model
@@ -124,14 +80,14 @@ docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyunc
 Add `--device ascend` in the serve command
 
 ```bash
-lmdeploy serve api_server --backend pytorch --device ascend --eager-mode OpenGVLab/InternVL2-2B
+lmdeploy serve api_server --backend pytorch --device ascend OpenGVLab/InternVL2-2B
 ```
 
 Run the following commands to launch docker container for lmdeploy VLM serving:
 
 ```bash
-docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend --eager-mode OpenGVLab/InternVL2-2B"
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend OpenGVLab/InternVL2-2B"
 ```
 
 ## Inference with Command line Interface
@@ -139,14 +95,14 @@ docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyunc
 Add `--device ascend` in the serve command.
 
 ```bash
-lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device ascend --eager-mode
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device ascend
 ```
 
 Run the following commands to launch lmdeploy chatting after starting container:
 
 ```bash
-docker exec -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy chat --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat"
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device ascend internlm/internlm2_5-7b-chat"
 ```
 
 ## Quantization
diff --git a/docs/en/get_started/camb/get_started.md b/docs/en/get_started/camb/get_started.md
new file mode 100644
index 0000000000..5b6e622667
--- /dev/null
+++ b/docs/en/get_started/camb/get_started.md
@@ -0,0 +1,99 @@
+# Cambricon
+
+The usage of lmdeploy on a Cambricon device is almost the same as its usage on CUDA with PytorchEngine in lmdeploy.
+Please read the original [Get Started](../get_started.md) guide before reading this tutorial.
+
+Here is the [supported model list](../../supported_models/supported_models.md#PyTorchEngine-on-Other-Platforms).
+
+> \[!IMPORTANT\]
+> We have uploaded a docker image to aliyun.
+> Please try to pull the image by following command:
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest`
+
+> \[!IMPORTANT\]
+> Currently, launching multi-device inference on Cambricon accelerators requires manually starting Ray.
+>
+> Below is an example for a 2-devices setup：
+>
+> ```shell
+>  export MLU_VISIBLE_DEVICES=0,1
+>  ray start --head --resources='{"MLU": 2}'
+> ```
+
+## Offline batch inference
+
+### LLM inference
+
+Set `device_type="camb"` in the `PytorchEngineConfig`:
+
+```python
+from lmdeploy import pipeline
+from lmdeploy import PytorchEngineConfig
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+        backend_config=PytorchEngineConfig(tp=1, device_type="camb"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
+```
+
+### VLM inference
+
+Set `device_type="camb"` in the `PytorchEngineConfig`:
+
+```python
+from lmdeploy import pipeline, PytorchEngineConfig
+from lmdeploy.vl import load_image
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+        backend_config=PytorchEngineConfig(tp=1, device_type='camb'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
+```
+
+## Online serving
+
+### Serve a LLM model
+
+Add `--device camb` in the serve command.
+
+```bash
+lmdeploy serve api_server --backend pytorch --device camb internlm/internlm2_5-7b-chat
+```
+
+Run the following commands to launch docker container for lmdeploy LLM serving:
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device camb internlm/internlm2_5-7b-chat"
+```
+
+### Serve a VLM model
+
+Add `--device camb` in the serve command
+
+```bash
+lmdeploy serve api_server --backend pytorch --device camb OpenGVLab/InternVL2-2B
+```
+
+Run the following commands to launch docker container for lmdeploy VLM serving:
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device camb OpenGVLab/InternVL2-2B"
+```
+
+## Inference with Command line Interface
+
+Add `--device camb` in the serve command.
+
+```bash
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device camb
+```
+
+Run the following commands to launch lmdeploy chatting after starting container:
+
+```bash
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device camb internlm/internlm2_5-7b-chat"
+```
diff --git a/docs/en/get_started/index.rst b/docs/en/get_started/index.rst
index 4343ee9ab1..1cb3bb78e2 100644
--- a/docs/en/get_started/index.rst
+++ b/docs/en/get_started/index.rst
@@ -3,6 +3,8 @@ On Other Platforms
 
 .. toctree::
    :maxdepth: 1
-   :caption: NPU(Huawei)
+   :caption: OtherPF
 
    ascend/get_started.md
+   maca/get_started.md
+   camb/get_started.md
diff --git a/docs/en/get_started/maca/get_started.md b/docs/en/get_started/maca/get_started.md
new file mode 100644
index 0000000000..5c647a379e
--- /dev/null
+++ b/docs/en/get_started/maca/get_started.md
@@ -0,0 +1,89 @@
+# MetaX-tech
+
+The usage of lmdeploy on a MetaX-tech device is almost the same as its usage on CUDA with PytorchEngine in lmdeploy.
+Please read the original [Get Started](../get_started.md) guide before reading this tutorial.
+
+Here is the [supported model list](../../supported_models/supported_models.md#PyTorchEngine-on-Other-Platforms).
+
+> \[!IMPORTANT\]
+> We have uploaded a docker image to aliyun.
+> Please try to pull the image by following command:
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest`
+
+## Offline batch inference
+
+### LLM inference
+
+Set `device_type="maca"` in the `PytorchEngineConfig`:
+
+```python
+from lmdeploy import pipeline
+from lmdeploy import PytorchEngineConfig
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+        backend_config=PytorchEngineConfig(tp=1, device_type="maca"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
+```
+
+### VLM inference
+
+Set `device_type="maca"` in the `PytorchEngineConfig`:
+
+```python
+from lmdeploy import pipeline, PytorchEngineConfig
+from lmdeploy.vl import load_image
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+        backend_config=PytorchEngineConfig(tp=1, device_type='maca'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
+```
+
+## Online serving
+
+### Serve a LLM model
+
+Add `--device maca` in the serve command.
+
+```bash
+lmdeploy serve api_server --backend pytorch --device maca internlm/internlm2_5-7b-chat
+```
+
+Run the following commands to launch docker container for lmdeploy LLM serving:
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device maca internlm/internlm2_5-7b-chat"
+```
+
+### Serve a VLM model
+
+Add `--device maca` in the serve command
+
+```bash
+lmdeploy serve api_server --backend pytorch --device maca OpenGVLab/InternVL2-2B
+```
+
+Run the following commands to launch docker container for lmdeploy VLM serving:
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device maca OpenGVLab/InternVL2-2B"
+```
+
+## Inference with Command line Interface
+
+Add `--device maca` in the serve command.
+
+```bash
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device maca
+```
+
+Run the following commands to launch lmdeploy chatting after starting container:
+
+```bash
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device maca internlm/internlm2_5-7b-chat"
+```
diff --git a/docs/en/supported_models/supported_models.md b/docs/en/supported_models/supported_models.md
index 2766fdb83d..38f02fb1fa 100644
--- a/docs/en/supported_models/supported_models.md
+++ b/docs/en/supported_models/supported_models.md
@@ -123,28 +123,28 @@ The following tables detail the models supported by LMDeploy's TurboMind engine
 * [2] PyTorch engine removes the support of original llava models after v0.6.4. Please use their corresponding transformers models instead, which can be found in https://huggingface.co/llava-hf
 ```
 
-## PyTorchEngine on Huawei Ascend Platform
+## PyTorchEngine on Other Platforms
 
-|                |           |      |  Atlas 800T A2   |  Atlas 800T A2   | Atlas 800T A2 | Atlas 800T A2 | Atlas 300I Duo |
-| :------------: | :-------: | :--: | :--------------: | :--------------: | :-----------: | :-----------: | :------------: |
-|     Model      |   Size    | Type | FP16/BF16(eager) | FP16/BF16(graph) |  W8A8(graph)  | W4A16(eager)  |  FP16(graph)   |
-|     Llama2     | 7B - 70B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |       -        |
-|     Llama3     |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    Llama3.1    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternLM2    | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  InternLM2.5   | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternLM3    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    Mixtral     |   8x7B    | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |
-|  QWen1.5-MoE   |   A2.7B   | LLM  |       Yes        |        -         |      No       |      No       |       -        |
-|   QWen2(.5)    |    7B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    QWen2-VL    |  2B, 7B   | MLLM |       Yes        |       Yes        |       -       |       -       |       -        |
-|   QWen2.5-VL   | 3B - 72B  | MLLM |       Yes        |       Yes        |       -       |       -       |      Yes       |
-|   QWen2-MoE    |  A14.57B  | LLM  |       Yes        |        -         |      No       |      No       |       -        |
-|     QWen3      | 0.6B-235B | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |
-|  DeepSeek-V2   |    16B    | LLM  |        No        |       Yes        |      No       |      No       |       -        |
-| InternVL(v1.5) |  2B-26B   | MLLM |       Yes        |        -         |      Yes      |      Yes      |       -        |
-|   InternVL2    |  1B-40B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  InternVL2.5   |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternVL3    |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  CogVLM2-chat  |    19B    | MLLM |       Yes        |        No        |       -       |       -       |       -        |
-|     GLM4V      |    9B     | MLLM |       Yes        |        No        |       -       |       -       |       -        |
+|                |           |      |  Atlas 800T A2   |  Atlas 800T A2   | Atlas 800T A2 | Atlas 800T A2 | Atlas 300I Duo |  Atlas 800T A3   | Maca C500 | Cambricon |
+| :------------: | :-------: | :--: | :--------------: | :--------------: | :-----------: | :-----------: | :------------: | :--------------: | :-------: | :-------: |
+|     Model      |   Size    | Type | FP16/BF16(eager) | FP16/BF16(graph) |  W8A8(graph)  | W4A16(eager)  |  FP16(graph)   | FP16/BF16(eager) |  BF/FP16  |  BF/FP16  |
+|     Llama2     | 7B - 70B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |       -        |       Yes        |    Yes    |    Yes    |
+|     Llama3     |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|    Llama3.1    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|   InternLM2    | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|  InternLM2.5   | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|   InternLM3    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|    Mixtral     |   8x7B    | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |        -         |    Yes    |    Yes    |
+|  QWen1.5-MoE   |   A2.7B   | LLM  |       Yes        |        -         |      No       |      No       |       -        |        -         |    Yes    |     -     |
+|   QWen2(.5)    |    7B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|    QWen2-VL    |  2B, 7B   | MLLM |       Yes        |       Yes        |       -       |       -       |       -        |        -         |    Yes    |    No     |
+|   QWen2.5-VL   | 3B - 72B  | MLLM |       Yes        |       Yes        |       -       |       -       |      Yes       |        -         |    Yes    |    No     |
+|   QWen2-MoE    |  A14.57B  | LLM  |       Yes        |        -         |      No       |      No       |       -        |        -         |    Yes    |     -     |
+|     QWen3      | 0.6B-235B | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |       Yes        |    Yes    |    Yes    |
+|  DeepSeek-V2   |    16B    | LLM  |        No        |       Yes        |      No       |      No       |       -        |        -         |     -     |     -     |
+| InternVL(v1.5) |  2B-26B   | MLLM |       Yes        |        -         |      Yes      |      Yes      |       -        |        -         |    Yes    |     -     |
+|   InternVL2    |  1B-40B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|  InternVL2.5   |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|   InternVL3    |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|  CogVLM2-chat  |    19B    | MLLM |       Yes        |        No        |       -       |       -       |       -        |        -         |    Yes    |     -     |
+|     GLM4V      |    9B     | MLLM |       Yes        |        No        |       -       |       -       |       -        |        -         |     -     |     -     |
diff --git a/docs/zh_cn/get_started/ascend/get_started.md b/docs/zh_cn/get_started/ascend/get_started.md
index e076e09fe5..bae1503470 100644
--- a/docs/zh_cn/get_started/ascend/get_started.md
+++ b/docs/zh_cn/get_started/ascend/get_started.md
@@ -1,69 +1,28 @@
-# 华为昇腾（Atlas 800T A2 & Atlas 300I Duo）
+# 华为昇腾
 
-我们基于 LMDeploy 的 PytorchEngine，增加了华为昇腾设备的支持。所以，在华为昇腾上使用 LDMeploy 的方法与在英伟达 GPU 上使用 PytorchEngine 后端的方法几乎相同。在阅读本教程之前，请先阅读原版的[快速开始](../get_started.md)。
+我们基于 LMDeploy 的 PytorchEngine，增加了华为昇腾设备的支持，目前支持的型号是**Atlas 800T A3，Atlas 800T A2和Atlas 300I Duo**。在华为昇腾上使用 LMDeploy 的方法与在英伟达 GPU 上使用 PytorchEngine 后端的方法几乎相同。在阅读本教程之前，请先阅读原版的[快速开始](../get_started.md)。
 
-支持的模型列表在[这里](../../supported_models/supported_models.md#PyTorchEngine-华为昇腾平台).
+支持的模型列表在[这里](../../supported_models/supported_models.md#PyTorchEngine-其他平台).
 
 > \[!IMPORTANT\]
-> 我们已经在阿里云上提供了构建完成的鲲鹏CPU版本的镜像(从lmdeploy 0.7.1 + dlinfer 0.1.6开始)。
+> 我们已经在阿里云上提供了构建完成的鲲鹏CPU版本的镜像。
 > 请使用下面的命令来拉取镜像:
+>
+> Atlas 800T A3:
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a3-latest`
+> （Atlas 800T A3目前只支持Qwen系列的算子模式下运行）
+>
 > Atlas 800T A2:
-> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:910b-latest`
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest`
+>
 > Atlas 300I Duo:
-> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:310p-latest`
-> 下述的dockerfile依然是可以执行的，您可以直接拉取镜像，也可以使用dockerfile来自己构建。
-
-## 安装
-
-我们强烈建议用户构建一个 Docker 镜像以简化环境设置。
-
-克隆 lmdeploy 的源代码，Dockerfile 位于 docker 目录中。
-
-```shell
-git clone https://github.com/InternLM/lmdeploy.git
-cd lmdeploy
-```
-
-### 环境准备
-
-Docker 版本应不低于 18.09。并且需按照[官方指南](https://www.hiascend.com/document/detail/zh/mindx-dl/600/clusterscheduling/clusterschedulingig/clusterschedulingig/dlug_installation_012.html)安装 Ascend Docker Runtime。
-
-> \[!CAUTION\]
-> 如果在后续容器内出现`libascend_hal.so: cannot open shared object file`错误，说明Ascend Docker Runtime没有被正确安装。
-
-#### Drivers，Firmware 和 CANN
-
-目标机器需安装华为驱动程序和固件版本至少为 23.0.3，请参考
-[CANN 驱动程序和固件安装](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha001/softwareinst/instg/instg_0005.html)
-和[下载资源](https://www.hiascend.com/hardware/firmware-drivers/community?product=4&model=26&cann=8.0.RC2.beta1&driver=1.0.25.alpha)。
-
-另外，`docker/Dockerfile_aarch64_ascend`没有提供CANN 安装包，用户需要自己从[昇腾资源下载中心](https://www.hiascend.com/developer/download/community/result?module=cann&cann=8.0.RC2.beta1&product=4&model=26)下载CANN(version 8.0.RC2.beta1)软件包。
-并将`Ascend-cann-kernels-910b*.run`，`Ascend-cann-nnal_*.run`和`Ascend-cann-toolkit*.run` 放在 lmdeploy 源码根目录下。
-
-#### 构建镜像
-
-请在 lmdeploy源 代码根目录下执行以下镜像构建命令，CANN 相关的安装包也放在此目录下。
-
-```bash
-DOCKER_BUILDKIT=1 docker build -t lmdeploy-aarch64-ascend:latest \
-    -f docker/Dockerfile_aarch64_ascend .
-```
-
-上述`Dockerfile_aarch64_ascend`适用于鲲鹏CPU. 如果是Intel CPU的机器，请尝试[这个dockerfile](https://github.com/InternLM/lmdeploy/issues/2745#issuecomment-2473285703) (未经过测试)
-
-如果以下命令执行没有任何错误，这表明环境设置成功。
-
-```bash
-docker run -e ASCEND_VISIBLE_DEVICES=0 --rm --name lmdeploy -t lmdeploy-aarch64-ascend:latest lmdeploy check_env
-```
-
-关于在昇腾设备上运行`docker run`命令的详情，请参考这篇[文档](https://www.hiascend.com/document/detail/zh/mindx-dl/600/clusterscheduling/dockerruntimeug/dlruntime_ug_013.html)。
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:300i-duo-latest`
+> （Atlas 300I Duo目前只支持非eager模式）
+>
+> 如果您希望自己构建环境，请参考[这里](../../../../docker)的dockerfile来自己构建。
 
 ## 离线批处理
 
-> \[!TIP\]
-> 图模式已经支持了Atlas 800T A2。用户可以设定`eager_mode=False`来开启图模式，或者设定`eager_mode=True`来关闭图模式。(启动图模式需要事先source `/usr/local/Ascend/nnal/atb/set_env.sh`)
-
 ### LLM 推理
 
 将`device_type="ascend"`加入`PytorchEngineConfig`的参数中。
@@ -71,12 +30,11 @@ docker run -e ASCEND_VISIBLE_DEVICES=0 --rm --name lmdeploy -t lmdeploy-aarch64-
 ```python
 from lmdeploy import pipeline
 from lmdeploy import PytorchEngineConfig
-if __name__ == "__main__":
-    pipe = pipeline("internlm/internlm2_5-7b-chat",
-                    backend_config=PytorchEngineConfig(tp=1, device_type="ascend", eager_mode=True))
-    question = ["Shanghai is", "Please introduce China", "How are you?"]
-    response = pipe(question)
-    print(response)
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+             backend_config=PytorchEngineConfig(tp=1, device_type="ascend"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
 ```
 
 ### VLM 推理
@@ -86,33 +44,28 @@ if __name__ == "__main__":
 ```python
 from lmdeploy import pipeline, PytorchEngineConfig
 from lmdeploy.vl import load_image
-if __name__ == "__main__":
-    pipe = pipeline('OpenGVLab/InternVL2-2B',
-                    backend_config=PytorchEngineConfig(tp=1, device_type='ascend', eager_mode=True))
-    image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-    response = pipe(('describe this image', image))
-    print(response)
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+     backend_config=PytorchEngineConfig(tp=1, device_type='ascend'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
 ```
 
 ## 在线服务
 
-> \[!TIP\]
-> 图模式已经支持Atlas 800T A2。
-> 在线服务时，图模式默认开启，用户可以添加`--eager-mode`来关闭图模式。(启动图模式需要事先source `/usr/local/Ascend/nnal/atb/set_env.sh`)
-
 ### LLM 模型服务
 
 将`--device ascend`加入到服务启动命令中。
 
 ```bash
-lmdeploy serve api_server --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat
+lmdeploy serve api_server --backend pytorch --device ascend internlm/internlm2_5-7b-chat
 ```
 
 也可以运行以下命令启动容器运行LLM模型服务。
 
 ```bash
-docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat"
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend internlm/internlm2_5-7b-chat"
 ```
 
 ### VLM 模型服务
@@ -120,14 +73,14 @@ docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyunc
 将`--device ascend`加入到服务启动命令中。
 
 ```bash
-lmdeploy serve api_server --backend pytorch --device ascend --eager-mode OpenGVLab/InternVL2-2B
+lmdeploy serve api_server --backend pytorch --device ascend OpenGVLab/InternVL2-2B
 ```
 
 也可以运行以下命令启动容器运行VLM模型服务。
 
 ```bash
-docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend --eager-mode OpenGVLab/InternVL2-2B"
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device ascend OpenGVLab/InternVL2-2B"
 ```
 
 ## 使用命令行与LLM模型对话
@@ -135,14 +88,14 @@ docker exec -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyunc
 将`--device ascend`加入到服务启动命令中。
 
 ```bash
-lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device ascend --eager-mode
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device ascend
 ```
 
 也可以运行以下命令使启动容器后开启lmdeploy聊天
 
 ```bash
-docker exec -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:latest \
-    bash -i -c "lmdeploy chat --backend pytorch --device ascend --eager-mode internlm/internlm2_5-7b-chat"
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/ascend:a2-latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device ascend internlm/internlm2_5-7b-chat"
 ```
 
 ## 量化
diff --git a/docs/zh_cn/get_started/camb/get_started.md b/docs/zh_cn/get_started/camb/get_started.md
new file mode 100644
index 0000000000..4f3043ccce
--- /dev/null
+++ b/docs/zh_cn/get_started/camb/get_started.md
@@ -0,0 +1,96 @@
+# 寒武纪云端加速卡
+
+我们基于 LMDeploy 的 PytorchEngine，增加了寒武纪云端加速卡设备的支持。所以，在寒武纪云端加速卡上使用 LMDeploy 的方法与在英伟达 GPU 上使用 PytorchEngine 后端的方法几乎相同。在阅读本教程之前，请先阅读原版的[快速开始](../get_started.md)。
+
+支持的模型列表在[这里](../../supported_models/supported_models.md#PyTorchEngine-其他平台).
+
+> \[!IMPORTANT\]
+> 我们已经在阿里云上提供了构建完成的寒武纪云端加速卡镜像。
+> 请使用下面的命令来拉取镜像:
+>
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest`
+
+> \[!IMPORTANT\]
+> 目前寒武纪加速卡上启动多卡推理需要手动启动ray。下面是一个2卡的例子：
+>
+> ```shell
+>  export MLU_VISIBLE_DEVICES=0,1
+>  ray start --head --resources='{"MLU": 2}'
+> ```
+
+## 离线批处理
+
+### LLM 推理
+
+将`device_type="camb"`加入`PytorchEngineConfig`的参数中。
+
+```python
+from lmdeploy import pipeline
+from lmdeploy import PytorchEngineConfig
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+             backend_config=PytorchEngineConfig(tp=1, device_type="camb"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
+```
+
+### VLM 推理
+
+将`device_type="camb"`加入`PytorchEngineConfig`的参数中。
+
+```python
+from lmdeploy import pipeline, PytorchEngineConfig
+from lmdeploy.vl import load_image
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+     backend_config=PytorchEngineConfig(tp=1, device_type='camb'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
+```
+
+## 在线服务
+
+### LLM 模型服务
+
+将`--device camb`加入到服务启动命令中。
+
+```bash
+lmdeploy serve api_server --backend pytorch --device camb internlm/internlm2_5-7b-chat
+```
+
+也可以运行以下命令启动容器运行LLM模型服务。
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device camb internlm/internlm2_5-7b-chat"
+```
+
+### VLM 模型服务
+
+将`--device camb`加入到服务启动命令中。
+
+```bash
+lmdeploy serve api_server --backend pytorch --device camb OpenGVLab/InternVL2-2B
+```
+
+也可以运行以下命令启动容器运行VLM模型服务。
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device camb OpenGVLab/InternVL2-2B"
+```
+
+## 使用命令行与LLM模型对话
+
+将`--device camb`加入到服务启动命令中。
+
+```bash
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device camb
+```
+
+也可以运行以下命令使启动容器后开启lmdeploy聊天
+
+```bash
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/camb:latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device camb internlm/internlm2_5-7b-chat"
+```
diff --git a/docs/zh_cn/get_started/index.rst b/docs/zh_cn/get_started/index.rst
index 35affc13ce..2a84b00684 100644
--- a/docs/zh_cn/get_started/index.rst
+++ b/docs/zh_cn/get_started/index.rst
@@ -3,6 +3,8 @@
 
 .. toctree::
    :maxdepth: 1
-   :caption: NPU(Huawei)
+   :caption: OtherPF
 
    ascend/get_started.md
+   maca/get_started.md
+   camb/get_started.md
diff --git a/docs/zh_cn/get_started/maca/get_started.md b/docs/zh_cn/get_started/maca/get_started.md
new file mode 100644
index 0000000000..bbe57caf7f
--- /dev/null
+++ b/docs/zh_cn/get_started/maca/get_started.md
@@ -0,0 +1,87 @@
+# 沐曦C500
+
+我们基于 LMDeploy 的 PytorchEngine，增加了沐曦C500设备的支持。所以，在沐曦上使用 LMDeploy 的方法与在英伟达 GPU 上使用 PytorchEngine 后端的方法几乎相同。在阅读本教程之前，请先阅读原版的[快速开始](../get_started.md)。
+
+支持的模型列表在[这里](../../supported_models/supported_models.md#PyTorchEngine-其他平台).
+
+> \[!IMPORTANT\]
+> 我们已经在阿里云上提供了构建完成的沐曦的镜像。
+> 请使用下面的命令来拉取镜像:
+> `docker pull crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest`
+
+## 离线批处理
+
+### LLM 推理
+
+将`device_type="maca"`加入`PytorchEngineConfig`的参数中。
+
+```python
+from lmdeploy import pipeline
+from lmdeploy import PytorchEngineConfig
+pipe = pipeline("internlm/internlm2_5-7b-chat",
+             backend_config=PytorchEngineConfig(tp=1, device_type="maca"))
+question = ["Shanghai is", "Please introduce China", "How are you?"]
+response = pipe(question)
+print(response)
+```
+
+### VLM 推理
+
+将`device_type="maca"`加入`PytorchEngineConfig`的参数中。
+
+```python
+from lmdeploy import pipeline, PytorchEngineConfig
+from lmdeploy.vl import load_image
+pipe = pipeline('OpenGVLab/InternVL2-2B',
+     backend_config=PytorchEngineConfig(tp=1, device_type='maca'))
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+response = pipe(('describe this image', image))
+print(response)
+```
+
+## 在线服务
+
+### LLM 模型服务
+
+将`--device maca`加入到服务启动命令中。
+
+```bash
+lmdeploy serve api_server --backend pytorch --device maca internlm/internlm2_5-7b-chat
+```
+
+也可以运行以下命令启动容器运行LLM模型服务。
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device maca internlm/internlm2_5-7b-chat"
+```
+
+### VLM 模型服务
+
+将`--device maca`加入到服务启动命令中。
+
+```bash
+lmdeploy serve api_server --backend pytorch --device maca OpenGVLab/InternVL2-2B
+```
+
+也可以运行以下命令启动容器运行VLM模型服务。
+
+```bash
+docker run -it --net=host crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy serve api_server --backend pytorch --device maca OpenGVLab/InternVL2-2B"
+```
+
+## 使用命令行与LLM模型对话
+
+将`--device maca`加入到服务启动命令中。
+
+```bash
+lmdeploy chat internlm/internlm2_5-7b-chat --backend pytorch --device maca
+```
+
+也可以运行以下命令使启动容器后开启lmdeploy聊天
+
+```bash
+docker run -it crpi-4crprmm5baj1v8iv.cn-hangzhou.personal.cr.aliyuncs.com/lmdeploy_dlinfer/maca:latest \
+    bash -i -c "lmdeploy chat --backend pytorch --device maca internlm/internlm2_5-7b-chat"
+```
diff --git a/docs/zh_cn/supported_models/supported_models.md b/docs/zh_cn/supported_models/supported_models.md
index 4d9998f2df..aaebb1df1a 100644
--- a/docs/zh_cn/supported_models/supported_models.md
+++ b/docs/zh_cn/supported_models/supported_models.md
@@ -123,28 +123,28 @@
 * [2] 自 0.6.4 之后，PyTorch 引擎移除了对 llava 模型原始格式的支持。我们建议使用它们对应的 transformers 格式的模型。这些模型可以在 https://huggingface.co/llava-hf 中找到
 ```
 
-## PyTorchEngine 华为昇腾平台
+## PyTorchEngine 其他平台
 
-|                |           |      |  Atlas 800T A2   |  Atlas 800T A2   | Atlas 800T A2 | Atlas 800T A2 | Atlas 300I Duo |
-| :------------: | :-------: | :--: | :--------------: | :--------------: | :-----------: | :-----------: | :------------: |
-|     Model      |   Size    | Type | FP16/BF16(eager) | FP16/BF16(graph) |  W8A8(graph)  | W4A16(eager)  |  FP16(graph)   |
-|     Llama2     | 7B - 70B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |       -        |
-|     Llama3     |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    Llama3.1    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternLM2    | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  InternLM2.5   | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternLM3    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    Mixtral     |   8x7B    | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |
-|  QWen1.5-MoE   |   A2.7B   | LLM  |       Yes        |        -         |      No       |      No       |       -        |
-|   QWen2(.5)    |    7B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|    QWen2-VL    |  2B, 7B   | MLLM |       Yes        |       Yes        |       -       |       -       |       -        |
-|   QWen2.5-VL   | 3B - 72B  | MLLM |       Yes        |       Yes        |       -       |       -       |      Yes       |
-|   QWen2-MoE    |  A14.57B  | LLM  |       Yes        |        -         |      No       |      No       |       -        |
-|     QWen3      | 0.6B-235B | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |
-|  DeepSeek-V2   |    16B    | LLM  |        No        |       Yes        |      No       |      No       |       -        |
-| InternVL(v1.5) |  2B-26B   | MLLM |       Yes        |        -         |      Yes      |      Yes      |       -        |
-|   InternVL2    |  1B-40B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  InternVL2.5   |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|   InternVL3    |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |
-|  CogVLM2-chat  |    19B    | MLLM |       Yes        |        No        |       -       |       -       |       -        |
-|     GLM4V      |    9B     | MLLM |       Yes        |        No        |       -       |       -       |       -        |
+|                |           |      |  Atlas 800T A2   |  Atlas 800T A2   | Atlas 800T A2 | Atlas 800T A2 | Atlas 300I Duo |  Atlas 800T A3   | Maca C500 | Cambricon |
+| :------------: | :-------: | :--: | :--------------: | :--------------: | :-----------: | :-----------: | :------------: | :--------------: | :-------: | :-------: |
+|     Model      |   Size    | Type | FP16/BF16(eager) | FP16/BF16(graph) |  W8A8(graph)  | W4A16(eager)  |  FP16(graph)   | FP16/BF16(eager) |  BF/FP16  |  BF/FP16  |
+|     Llama2     | 7B - 70B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |       -        |       Yes        |    Yes    |    Yes    |
+|     Llama3     |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|    Llama3.1    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|   InternLM2    | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|  InternLM2.5   | 7B - 20B  | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|   InternLM3    |    8B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |       Yes        |    Yes    |    Yes    |
+|    Mixtral     |   8x7B    | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |        -         |    Yes    |    Yes    |
+|  QWen1.5-MoE   |   A2.7B   | LLM  |       Yes        |        -         |      No       |      No       |       -        |        -         |    Yes    |     -     |
+|   QWen2(.5)    |    7B     | LLM  |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|    QWen2-VL    |  2B, 7B   | MLLM |       Yes        |       Yes        |       -       |       -       |       -        |        -         |    Yes    |    No     |
+|   QWen2.5-VL   | 3B - 72B  | MLLM |       Yes        |       Yes        |       -       |       -       |      Yes       |        -         |    Yes    |    No     |
+|   QWen2-MoE    |  A14.57B  | LLM  |       Yes        |        -         |      No       |      No       |       -        |        -         |    Yes    |     -     |
+|     QWen3      | 0.6B-235B | LLM  |       Yes        |       Yes        |      No       |      No       |      Yes       |       Yes        |    Yes    |    Yes    |
+|  DeepSeek-V2   |    16B    | LLM  |        No        |       Yes        |      No       |      No       |       -        |        -         |     -     |     -     |
+| InternVL(v1.5) |  2B-26B   | MLLM |       Yes        |        -         |      Yes      |      Yes      |       -        |        -         |    Yes    |     -     |
+|   InternVL2    |  1B-40B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|  InternVL2.5   |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|   InternVL3    |  1B-78B   | MLLM |       Yes        |       Yes        |      Yes      |      Yes      |      Yes       |        -         |    Yes    |    Yes    |
+|  CogVLM2-chat  |    19B    | MLLM |       Yes        |        No        |       -       |       -       |       -        |        -         |    Yes    |     -     |
+|     GLM4V      |    9B     | MLLM |       Yes        |        No        |       -       |       -       |       -        |        -         |     -     |     -     |