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>
15 lines
204 B
Plaintext
15 lines
204 B
Plaintext
# Common dependencies
|
|
-r common.txt
|
|
|
|
# Dependencies for TPU
|
|
cmake>=3.26.1
|
|
packaging>=24.2
|
|
setuptools-scm>=8
|
|
wheel
|
|
jinja2>=3.1.6
|
|
ray[default]
|
|
ray[data]
|
|
setuptools==78.1.0
|
|
nixl==0.3.0
|
|
tpu-inference==0.12.0
|