Update README.md

README.md

@@ -20,8 +20,8 @@ tags:
 ## Introduction
 
 Today, we are officially open-sourcing Ring-mini-linear-2.0.
-This model continues to employ a hybrid architecture that combines linear attention and standard attention mechanisms, striking a balance between performance and efficiency. Inheriting the efficient MoE (Mixture-of-Experts) design from the Ling 2.0 series, and through architectural optimizations such as a 1/32 expert activation ratio and MTP layers, Ring-mini-linear achieves the performance of an ~8B dense model while activating only 1.4B of its 16B total parameters. This model is continually trained from Ling-mini-base-2.0.
-In terms of performance, the hybrid linear model is comparable in overall performance to standard attention models of a similar size (e.g., ring-mini-2) and surpasses other open-source MoE and Dense models of the same class on several challenging benchmarks. Furthermore, it natively supports a 128k long context window, demonstrating superior speed and accuracy, especially on tasks involving long inputs and outputs.
+
+This model continues to employ a hybrid architecture that combines linear attention and standard attention mechanisms, striking a balance between performance and efficiency. Inheriting the efficient MoE (Mixture-of-Experts) design from the Ling 2.0 series, and through architectural optimizations such as a 1/32 expert activation ratio and MTP layers, Ring-mini-linear achieves the performance of an ~8B dense model while activating only 1.4B of its 16B total parameters. This model was converted from [Ling-mini-base-2.0](https://huggingface.co/inclusionAI/Ling-mini-base-2.0-20T), continually trained on an additional 600B tokens. In terms of performance, the hybrid linear model is comparable in overall performance to standard attention models of a similar size (e.g., Ring-mini-2) and surpasses other open-source MoE and Dense models of the same class on several challenging benchmarks. Furthermore, it natively supports a 128k long context window, demonstrating superior speed and accuracy, especially on tasks involving long inputs and outputs.
 
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
@@ -32,11 +32,11 @@ In terms of performance, the hybrid linear model is comparable in overall perfor
 
 ## Evaluation
 
-To better demonstrate our model's reasoning capabilities, we compared it with three other models—Ring-mini-2.0, Qwen3-8B-thinking, and GPT-OSS-20B-Medium—on 5 challenging reasoning benchmarks across mathematics, code, and science. We observe that the hybrid-linear architecture achieves performance comparable to that of softmax attention.
+To better demonstrate our model's reasoning capabilities, we compared it with three other models—Ring-mini-2.0, Qwen3-8B-thinking, and GPT-OSS-20B-Medium—on 5 challenging reasoning benchmarks across mathematics, code, and science. We observe that the hybrid-linear architecture achieves performance comparable to that of softmax attention models.
 
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
-    <img src="https://mdn.alipayobjects.com/huamei_jcuiuk/afts/img/4T3LQaJ2a1AAAAAAagAAAAgADr6CAQFr/original" width="1000">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/RcHlh5PriRuOLsErG8RjK.webp" width="1000">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 2:</strong> Model Performance Comparison </p>
   </div>
 </div>
@@ -48,29 +48,19 @@ The results are remarkable. In the prefill stage, Ring-mini-linear-2.0's perform
 
 <div style="display: flex; justify-content: center; align-items: flex-start; gap: 20px;">
   <div style="text-align: center;">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/O9gHLIOCdpWvBbPC6bMM5.webp" width="500">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/yHVE-nmTgV3w0z4X2eg_g.png" width="500">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 4:</strong> Ring-mini-linear-2.0 prefill throughput</p>
   </div>
   
   <div style="text-align: center;">
     <p align="center">
-      <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/AvMTStWFX-Frzv-vOzyr6.webp" width="500">
+      <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/mTqsHh0yFtQjpCN_fw4e0.png" width="500">
     </p>
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 5:</strong> Ring-mini-linear-2.0 decode throughput</p>
   </div>
 
 </div>
 
-
-## Model Downloads
-
-<div align="center">
-
-|     **Model**      | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
-| :----------------: | :---------------: | :-------------------: | :----------------: | :----------: |
-| Ring-mini-linear-2.0 |       16B       |         1.4B         |        128K         |      [🤗 HuggingFace](https://huggingface.co/inclusionAI/Ring-mini-linear-2.0) <br>[🤖 Modelscope](https://modelscope.cn/models/inclusionAI/Ring-mini-linear-2.0)|
-</div>
-
 ## Quickstart
 
 ### Requirements
@@ -143,7 +133,7 @@ pip3 install sgl-kernel==0.3.9.post2 vllm==0.10.2
 
 Then you should install our sglang whl package:
 ```shell
-pip install https://github.com/inclusionAI/Ring-V2/blob/main/hybrid_linear/whls/sglang-0.5.2-py3-none-any.whl
+pip install https://raw.githubusercontent.com/inclusionAI/Ring-V2/main/hybrid_linear/whls/sglang-0.5.2-py3-none-any.whl --no-deps --force-reinstall
 ```
 
 #### Run Inference
@@ -170,6 +160,56 @@ curl -s http://localhost:${PORT}/v1/chat/completions \
 
 More usage can be found [here](https://docs.sglang.ai/basic_usage/send_request.html)
 
-### vLLM
-TODO
+### 🚀 vLLM
+
+#### Environment Preparation
+
+Since the Pull Request (PR) has not been submitted to the vLLM community at this stage, please prepare the environment by following the steps below:
+```shell
+pip install torch==2.7.0 torchvision==0.22.0 
+```
+
+Then you should install our vLLM wheel package:
+```shell
+pip install https://github.com/inclusionAI/Ring-V2/blob/main/hybrid_linear/whls/vllm-0.8.5%2Bcuda12_8_gcc10_2_1-cp310-cp310-linux_x86_64.whl --no-deps --force-reinstall
+```
+
+#### Offline Inference
+
+```python
+from transformers import AutoTokenizer
+from vllm import LLM, SamplingParams
+
+tokenizer = AutoTokenizer.from_pretrained("inclusionAI/Ring-mini-linear-2.0")
+
+sampling_params = SamplingParams(temperature=0.7, top_p=0.8, repetition_penalty=1.05, max_tokens=16384)
+
+llm = LLM(model="inclusionAI/Ring-mini-linear-2.0", dtype='bfloat16', enable_prefix_caching=False, max_num_seqs=128)
+prompt = "Give me a short introduction to large language models."
+messages = [
+    {"role": "system", "content": "You are Ling, an assistant created by inclusionAI"},
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+outputs = llm.generate([text], sampling_params)
+```
+
+#### Online Inference
+```shell
+vllm serve inclusionAI/Ring-mini-linear-2.0 \
+              --tensor-parallel-size 2 \
+              --pipeline-parallel-size 1 \
+              --gpu-memory-utilization 0.90 \
+              --max-num-seqs 512 \
+              --no-enable-prefix-caching
+```
+
+
+For more information, please see our [GitHub](https://github.com/inclusionAI/Ring-V2/blob/main/hybrid_linear/README.md).
+
 ## Citation