abhai

README.md

@@ -28,7 +28,7 @@ We are seeing strong performance in terms of both parameter efficiency and infer
 
 ![Qwen3-Next-80B-A3B-Instruct Benchmark Comparison](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-Next/Qwen3-Next-80B-A3B-Instruct.001.jpeg)
 
-For more details, please refer to our blog post [Qwen3-Next](https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list).
+For more details, please refer to our blog post [Qwen3-Next](https://qwenlm.github.io/blog/qwen3_next/).
 
 ## Model Overview
 
@@ -40,9 +40,9 @@ For more details, please refer to our blog post [Qwen3-Next](https://qwen.ai/blo
 - Training Stage: Pretraining (15T tokens) & Post-training
 - Number of Parameters: 80B in total and 3B activated
 - Number of Paramaters (Non-Embedding): 79B
-- Hidden Dimension: 2048
 - Number of Layers: 48
-  - Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> 1 \* (Gated Attention -> MoE))
+- Hidden Dimension: 2048
+- Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> (Gated Attention -> MoE))
 - Gated Attention:
   - Number of Attention Heads: 16 for Q and 2 for KV
   - Head Dimension: 256
@@ -157,7 +157,7 @@ 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 links for detailed instructions and requirements.
+> See the above links for detailed instructions and requirements.
 
 
 ## Deployment
@@ -169,52 +169,52 @@ 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>=0.5.2` is required for Qwen3-Next, which can be installed using:
+SGLang has supported Qwen3-Next in its `main` branch, which can be installed from source:
 ```shell
-pip install 'sglang[all]>=0.5.2'
+pip install 'sglang[all] @ git+https://github.com/sgl-project/sglang.git@main#subdirectory=python'
 ```
-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
-python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8
+SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8
 ```
 
 The following command is recommended for MTP with the rest settings the same as above:
 ```shell
-python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
 ```
 
 > [!Note]
-> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
+> The environment variable `SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1` is required at the moment.
 
-Please also refer to SGLang's usage guide on [Qwen3-Next](https://docs.sglang.ai/basic_usage/qwen3.html).
+> [!Note]
+> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fail to start.
 
 ### 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>=0.10.2` is required for Qwen3-Next, which can be installed using:
+vLLM has supported Qwen3-Next in its `main` branch, which can be installed from source:
 ```shell
-pip install 'vllm>=0.10.2'
+pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 ```
-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 serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144
 ```
 
 The following command is recommended for MTP with the rest settings the same as above:
 ```shell
-vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
 ```
 
 > [!Note]
-> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
+> The environment variable `VLLM_ALLOW_LONG_MAX_MODEL_LEN=1` is required at the moment.
 
-Please also refer to vLLM's usage guide on [Qwen3-Next](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3-Next.html).
+> [!Note]
+> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fail to start.
 
 ## Agentic Use
 

tokenizer_config.json

@@ -226,7 +226,7 @@
         "<|video_pad|>"
     ],
     "bos_token": null,
-    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
     "clean_up_tokenization_spaces": false,
     "eos_token": "<|im_end|>",
     "errors": "replace",