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>
13 lines
524 B
Django/Jinja
13 lines
524 B
Django/Jinja
{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}
|
|
|
|
{%- for message in messages -%}
|
|
{%- if message['role'] == 'user' -%}
|
|
{{- '<reserved_106>' + message['content'] -}}
|
|
{%- elif message['role'] == 'assistant' -%}
|
|
{{- '<reserved_107>' + message['content'] -}}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
|
|
{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
|
|
{{- '<reserved_107>' -}}
|
|
{% endif %} |