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>
22 lines
670 B
YAML
22 lines
670 B
YAML
# scale-config.yml:
|
|
# Powers what instance types are available for GHA auto-scaled
|
|
# runners. Runners listed here will be available as self hosted
|
|
# runners, configuration is directly pulled from the main branch.
|
|
# runner_types:
|
|
# runner_label:
|
|
# instance_type: m4.large
|
|
# os: linux
|
|
# # min_available defaults to the global cfg in the ALI Terraform
|
|
# min_available: undefined
|
|
# # when max_available value is not defined, no max runners is enforced
|
|
# max_available: undefined
|
|
# disk_size: 50
|
|
# is_ephemeral: true
|
|
|
|
runner_types:
|
|
linux.2xlarge:
|
|
disk_size: 150
|
|
instance_type: c5.2xlarge
|
|
is_ephemeral: true
|
|
os: linux
|