software-engineering/spark-vllm-docker
2
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity

Add chat template and recipe for Qwen3.6-35B-A3B-FP8 model

Browse Source
This commit is contained in:
Eugene Rakhmatulin
2026-05-06 10:32:46 -07:00
parent 9fbed882bc
commit c67c5b5c1e
4 changed files with 328 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

223
mods/fix-qwen3.6-chat-template/chat_template.jinja Normal file
View File

@@ -0,0 +1,223 @@
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id is defined and add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id is defined and add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- set ns_flags = namespace(enable_thinking=true) %}
{%- if enable_thinking is defined %}
{%- set ns_flags.enable_thinking = enable_thinking %}
{%- endif %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if '<|think_off|>' in content %}
{%- set ns_flags.enable_thinking = false %}
{%- set content = content.replace('<|think_off|>', '') %}
{%- endif %}
{%- if '<|think_on|>' in content %}
{%- set ns_flags.enable_thinking = true %}
{%- set content = content.replace('<|think_on|>', '') %}
{%- endif %}
{%- set content = content.strip() %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if '<|think_off|>' in content %}
{%- set ns_flags.enable_thinking = false %}
{%- set content = content.replace('<|think_off|>', '') %}
{%- endif %}
{%- if '<|think_on|>' in content %}
{%- set ns_flags.enable_thinking = true %}
{%- set content = content.replace('<|think_on|>', '') %}
{%- endif %}
{%- set content = content.strip() %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{%- set ns.last_query_index = messages|length - 1 %}
{%- endif %}
{%- for message in messages %}
{%- set content = render_content(message.content, true)|trim %}
{%- if '<|think_off|>' in content %}
{%- set ns_flags.enable_thinking = false %}
{%- set content = content.replace('<|think_off|>', '') %}
{%- endif %}
{%- if '<|think_on|>' in content %}
{%- set ns_flags.enable_thinking = true %}
{%- set content = content.replace('<|think_on|>', '') %}
{%- endif %}
{%- set content = content.strip() %}
{%- if message.role == "system" or message.role == "developer" %}
{%- if not loop.first %}
{{- raise_exception('System message must be at the beginning.') }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{#- Auto-close unclosed think before tool_call -#}
{%- if '<think>' in content and '<tool_call>' in content %}
{%- set last_think = content.rfind('<think>') %}
{%- set last_close = content.rfind('</think>') %}
{%- set tool_pos = content.find('<tool_call>') %}
{%- if last_close < last_think or last_close == -1 %}
{%- if tool_pos > last_think %}
{%- set content = content[:tool_pos] + '</think>' + content[tool_pos:] %}
{%- else %}
{%- set content = content + '</think>' %}
{%- endif %}
{%- endif %}
{%- endif %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- set has_think_tag = false %}
{%- set think_end_token = '</think>' %}
{%- if '</think>' in content %}
{%- set has_think_tag = true %}
{%- elif '</thinking>' in content %}
{%- set has_think_tag = true %}
{%- set think_end_token = '</thinking>' %}
{%- elif '<think>' in content %}
{%- set reasoning_content = content.split('<think>')[-1].lstrip('\n') %}
{%- set content = '' %}
{%- endif %}
{%- if has_think_tag %}
{%- set reasoning_content = content.split(think_end_token)[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split(think_end_token)[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- set show_think = false %}
{%- if loop.index0 > ns.last_query_index %}
{%- set show_think = true %}
{%- elif ns_flags.enable_thinking and (preserve_thinking is undefined or preserve_thinking is true) and reasoning_content|length > 0 %}
{%- set show_think = true %}
{%- endif %}
{%- if show_think %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
{%- if tool_call.arguments|length > 0 %}
{%- for args_name in tool_call.arguments %}
{%- set args_value = tool_call.arguments[args_name] %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{%- elif tool_call.arguments is defined and tool_call.arguments is string %}
{%- if tool_call.arguments|trim|length > 0 %}
{{- tool_call.arguments }}
{{- '\n' }}
{%- endif %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if ns_flags.enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- else %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}

4
mods/fix-qwen3.6-chat-template/run.sh Normal file
View File

@@ -0,0 +1,4 @@
#!/bin/bash
set -e
cp chat_template.jinja $WORKSPACE_DIR/fixed_chat_template.jinja
echo "=======> to apply chat template, use --chat-template fixed_chat_template.jinja"

51
recipes/qwen3.6-35b-a3b-fp8-dflash.yaml Normal file
View File

@@ -0,0 +1,51 @@
# Recipe: Qwen/Qwen3.5-35B-A3B-FP8
# Qwen/Qwen3.5-35B-A3B model in native FP8 format
recipe_version: "1"
name: Qwen36-35B-A3B
description: vLLM serving Qwen3.6-35B-A3B-FP8
# HuggingFace model to download (optional, for --download-model)
model: Qwen/Qwen3.6-35B-A3B-FP8
#solo_only: true
# Container image to use
container: vllm-node
# Mod required to fix slowness and crash in the cluster (tracking https://github.com/vllm-project/vllm/issues/33857)
mods:
- mods/fix-qwen3.6-chat-template
# Default settings (can be overridden via CLI)
defaults:
port: 8000
host: 0.0.0.0
tensor_parallel: 2
gpu_memory_utilization: 0.7
max_model_len: 262144
max_num_batched_tokens: 16384
# Environment variables
env:
VLLM_MARLIN_USE_ATOMIC_ADD: 1
# The vLLM serve command template
command: |
vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
--host {host} \
--port {port} \
--max-model-len {max_model_len} \
--max-num-batched-tokens {max_num_batched_tokens} \
--gpu-memory-utilization {gpu_memory_utilization} \
--enable-auto-tool-choice \
--tool-call-parser qwen3_xml \
--reasoning-parser qwen3 \
--load-format fastsafetensors \
--attention-backend flash_attn \
--enable-prefix-caching \
--chat-template fixed_chat_template.jinja \
--speculative-config '{{"method": "dflash", "model": "z-lab/Qwen3.5-35B-A3B-DFlash", "num_speculative_tokens": 15}}' \
-tp {tensor_parallel} \
--distributed-executor-backend ray

50
recipes/qwen3.6-35b-a3b-fp8.yaml Normal file
View File

@@ -0,0 +1,50 @@
# Recipe: Qwen/Qwen3.5-35B-A3B-FP8
# Qwen/Qwen3.5-35B-A3B model in native FP8 format
recipe_version: "1"
name: Qwen36-35B-A3B
description: vLLM serving Qwen3.6-35B-A3B-FP8
# HuggingFace model to download (optional, for --download-model)
model: Qwen/Qwen3.6-35B-A3B-FP8
#solo_only: true
# Container image to use
container: vllm-node
# Mod required to fix slowness and crash in the cluster (tracking https://github.com/vllm-project/vllm/issues/33857)
mods:
- mods/fix-qwen3.6-chat-template
# Default settings (can be overridden via CLI)
defaults:
port: 8000
host: 0.0.0.0
tensor_parallel: 2
gpu_memory_utilization: 0.7
max_model_len: 262144
max_num_batched_tokens: 16384
# Environment variables
env:
VLLM_MARLIN_USE_ATOMIC_ADD: 1
# The vLLM serve command template
command: |
vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
--host {host} \
--port {port} \
--max-model-len {max_model_len} \
--max-num-batched-tokens {max_num_batched_tokens} \
--gpu-memory-utilization {gpu_memory_utilization} \
--enable-auto-tool-choice \
--tool-call-parser qwen3_xml \
--kv-cache-dtype fp8 \
--load-format fastsafetensors \
--attention-backend flashinfer \
--enable-prefix-caching \
--chat-template fixed_chat_template.jinja \
-tp {tensor_parallel} \
--distributed-executor-backend ray