Add vLLM v0.18.1 source tree with KV transfer abort fix

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>
This commit is contained in:
2026-05-22 00:30:38 +08:00
parent b6591950bc
commit 445e491123
4285 changed files with 1111303 additions and 1 deletions

View File

@@ -0,0 +1,12 @@
{%- for message in messages %}
{%- if message['role'] == 'user' %}
{{- '<_user>' + message['content']|trim }}
{%- elif message['role'] == 'system' %}
{{- '<_system>' + message['content']|trim }}
{%- elif message['role'] == 'assistant' %}
{{- '<_bot>' + message['content'] }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<_bot>' }}
{%- endif %}