Update README.md

README.md

@@ -29,7 +29,7 @@ We are seeing strong performance in terms of both parameter efficiency and infer
 
 ![Qwen3-Next-80B-A3B-Thinking Benchmark Comparison](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-Next/Qwen3-Next-80B-A3B-Thinking.001.jpeg)
 
-For more details, please refer to our blog post [Qwen3-Next](https://qwenlm.github.io/blog/qwen3_next/).
+For more details, please refer to our blog post [Qwen3-Next](https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list).
 
 ## Model Overview
 
@@ -48,9 +48,9 @@ For more details, please refer to our blog post [Qwen3-Next](https://qwenlm.gith
 - Training Stage: Pretraining (15T tokens) & Post-training
 - Number of Parameters: 80B in total and 3B activated
 - Number of Paramaters (Non-Embedding): 79B
-- Number of Layers: 48
 - Hidden Dimension: 2048
-- Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> (Gated Attention -> MoE))
+- Number of Layers: 48
+  - Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> 1 \* (Gated Attention -> MoE))
 - Gated Attention:
   - Number of Attention Heads: 16 for Q and 2 for KV
   - Head Dimension: 256
@@ -173,7 +173,7 @@ print("content:", content)
 
 > [!Tip]
 > Depending on the inference settings, you may observe better efficiency with [`flash-linear-attention`](https://github.com/fla-org/flash-linear-attention#installation) and [`causal-conv1d`](https://github.com/Dao-AILab/causal-conv1d).
-> See the above links for detailed instructions and requirements.
+> See the links for detailed instructions and requirements.
 
 ## Deployment
 
@@ -184,57 +184,58 @@ For deployment, you can use the latest `sglang` or `vllm` to create an OpenAI-co
 [SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
 SGLang could be used to launch a server with OpenAI-compatible API service. 
 
-SGLang has supported Qwen3-Next in its `main` branch, which can be installed from source:
+`sglang>=0.5.2` is required for Qwen3-Next, which can be installed using:
 ```shell
-pip install 'sglang[all] @ git+https://github.com/sgl-project/sglang.git@main#subdirectory=python'
+pip install 'sglang[all]>=0.5.2'
 ```
+See [its documentation](https://docs.sglang.ai/get_started/install.html) for more details.
 
 The following command can be used to create an API endpoint at `http://localhost:30000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
 ```shell
-SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8
+python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8
 ```
 
 The following command is recommended for MTP with the rest settings the same as above:
 ```shell
-SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Thinking --port 30000 --tp-size 4 --context-length 262144 --reasoning-parser deepseek-r1 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
 ```
 
-> [!Note]
-> The environment variable `SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1` is required at the moment.
-
 > [!Note]
 > The default context length is 256K. 
 > If you encounter out-of-memory (OOM) issues, you may consider reducing the context length to a smaller value. 
 > However, since the model may require longer token sequences for reasoning, we strongly recommend using a context length greater than 131,072.
 
+Please also refer to SGLang's usage guide on [Qwen3-Next](https://docs.sglang.ai/basic_usage/qwen3.html).
+
 ### vLLM
 
 [vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
 vLLM could be used to launch a server with OpenAI-compatible API service. 
 
-vLLM has supported Qwen3-Next in its `main` branch, which can be installed from source:
+`vllm>=0.10.2` is required for Qwen3-Next, which can be installed using:
 ```shell
-pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
+pip install 'vllm>=0.10.2'
 ```
+See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details.
 
 The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
 ```shell
-VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1
+vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1
 ```
 
 The following command is recommended for MTP with the rest settings the same as above:
 ```shell
-VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
+vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser deepseek_r1 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
 ```
 
-> [!Note]
-> The environment variable `VLLM_ALLOW_LONG_MAX_MODEL_LEN=1` is required at the moment.
-
 > [!Note]
 > The default context length is 256K. 
 > If you encounter out-of-memory (OOM) issues, you may consider reducing the context length to a smaller value. 
 > However, since the model may require longer token sequences for reasoning, we strongly recommend using a context length greater than 131,072 when possible.
 
+Please also refer to vLLM's usage guide on [Qwen3-Next](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3-Next.html).
+
+
 ## Agentic Use
 
 Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
@@ -252,7 +253,7 @@ llm_cfg = {
 
 # Using OpenAI-compatible API endpoint. It is recommended to disable the reasoning and the tool call parsing
 # functionality of the deployment frameworks and let Qwen-Agent automate the related operations. For example, 
-# `VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --served-model-name Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144`.
+# `vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --served-model-name Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144`.
 #
 # llm_cfg = {
 #     'model': 'Qwen3-Next-80B-A3B-Thinking',