Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
37 lines
1.3 KiB
Django/Jinja
37 lines
1.3 KiB
Django/Jinja
{%- if tools %}
|
|
{{- '<|start_of_role|>available_tools<|end_of_role|>
|
|
' }}
|
|
{%- for tool in tools %}
|
|
{{- tool | tojson(indent=4) }}
|
|
{%- if not loop.last %}
|
|
{{- '
|
|
|
|
' }}
|
|
{%- endif %}
|
|
{%- endfor %}
|
|
{{- '<|end_of_text|>
|
|
' }}
|
|
{%- endif %}
|
|
|
|
{%- for message in messages %}
|
|
{%- if message['role'] == 'system' %}
|
|
{{- '<|start_of_role|>system<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
|
' }}
|
|
{%- elif message['role'] == 'user' %}
|
|
{{- '<|start_of_role|>user<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
|
' }}
|
|
{%- elif message['role'] == 'assistant_tool_call' or (message['role'] == 'assistant' and message.tool_calls is defined) %}
|
|
{{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message.tool_calls|map(attribute='function')|list|tojson(indent=4) + '<|end_of_text|>
|
|
' }}
|
|
{%- elif message['role'] == 'assistant' %}
|
|
{{- '<|start_of_role|>assistant<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
|
' }}
|
|
{%- elif message['role'] == 'tool_response' or message['role'] == 'tool' %}
|
|
{{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
|
' }}
|
|
{%- endif %}
|
|
{%- if loop.last and add_generation_prompt %}
|
|
{{- '<|start_of_role|>assistant<|end_of_role|>' }}
|
|
{%- endif %}
|
|
{%- endfor %}
|