Update README.md

README.md

@@ -19,10 +19,9 @@ tags:
 
 ## Introduction
 
-We are excited to announce the official open-source release of Ring-mini-linear-2.0!
-
-Building on the success of our Ling 2.0 series, this model continues to leverage a powerful hybrid architecture of linear and standard attention, perfectly balancing high performance with superior efficiency. By integrating our proven MoE design with optimizations like a 1/32 expert activation ratio and MTP layers, Ring-mini-linear achieves the performance of a 8 B dense model while activating only 1.4 B parameters.  This model was converted from [Ling-mini-base-2.0](https://huggingface.co/inclusionAI/Ling-mini-base-2.0-20T), further trained on an additional 600 B tokens.
-When it comes to benchmarks, Ring-mini-linear-2.0 not only holds its own against standard attention models (like ring-mini-2) but also outperforms other open-source MoE and Dense models in its class on several demanding tasks. Plus, with native support for a 128k long context, it's faster and more precise than ever, especially when handling long-form inputs and outputs.
+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.
 
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
@@ -32,23 +31,16 @@ When it comes to benchmarks, Ring-mini-linear-2.0 not only holds its own against
 </div>
 
 ## Evaluation
-To properly evaluate the model's reasoning capabilities, we compared it against 3 other models—Ring-mini-2.0, Qwen3-8B-thinking, and GPT-OSS-20B-Medium—on 6 challenging reasoning benchmarks spanning mathematics, coding, and science. The results demonstrate that the performance of the hybrid linear architecture is by no means inferior to that of standard softmax attention; in fact, it even outperforms the other models on 3 of the benchmarks.
-<div style="display: flex; justify-content: center;">
-  <div style="text-align: center;">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/_tjjgBEBlankfrWUY0N9i.png" width="800">
-    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 2:</strong> Model Performance Comparison </p>
-  </div>
-</div>
 
-Here is a demo of a small Snake game, with the code generated by our model.
+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 mixed-linear architecture achieves performance comparable to that of softmax attention.
+
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
-    <img src="https://mdn.alipayobjects.com/huamei_jcuiuk/afts/img/tqfCQoTqRdAAAAAAgZAAAAgADr6CAQFr/original" width="800">
-    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 3:</strong> Snake Game </p>
+    <img src="https://mdn.alipayobjects.com/huamei_jcuiuk/afts/img/4T3LQaJ2a1AAAAAAagAAAAgADr6CAQFr/original" width="1000">
+    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 2:</strong> Model Performance Comparison </p>
   </div>
 </div>
 
-
 ## Linear Attention, Highly Sparse，High-Speed Generation
 
 Thanks to its hybrid attention mechanism and highly sparse MoE architecture, Ring-mini-linear-2.0 achieves near-linear time complexity and constant space complexity, resulting in outstanding inference efficiency. To fully demonstrate this advantage, we conducted a head-to-head comparison between our model and top-tier competitors of similar size or performance.
@@ -140,8 +132,26 @@ print(responses)
 print("*" * 30)
 ```
 
-### SGLang
-```bash
+### 🚀 SGLang
+
+#### Environment Preparation
+
+We will later submit our model to SGLang official release, now we can prepare the environment following steps:
+```shell
+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
+```
+
+#### Run Inference
+
+BF16 and FP8 models are supported by SGLang now, it depends on the dtype of the model in ${MODEL_PATH}. They both share the same command in the following:  
+
+- Start server:
+```shell
 python -m sglang.launch_server \
     --model-path <model_path> \
     --trust-remote-code \
@@ -149,6 +159,17 @@ python -m sglang.launch_server \
     --disable-radix-cache \
     --json-model-override-args "{\"linear_backend\": \"seg_la\"}"
 ```
+
+- Client:
+
+```shell
+curl -s http://localhost:${PORT}/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{"model": "auto", "messages": [{"role": "user", "content": "What is the capital of France?"}]}'
+```
+
+More usage can be found [here](https://docs.sglang.ai/basic_usage/send_request.html)
+
 ### vLLM
- 
+TODO
 ## Citation