A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Add scale_config.yml file for Meta autoscalers for GH Actions (#23840)
Signed-off-by: Jean Schmidt <contato@jschmidt.me>
Jean Schmidt committed
Aug 28, 2025 at 18:31 UTC
8805ad9fa9c04b2ce4e2a9adc217471798b1ae64
1 file changed
+21
.github/scale-config.yml
new
+21
@@ -0,0 +1,21 @@
1
+# scale-config.yml:
2
+# Powers what instance types are available for GHA auto-scaled
3
+# runners. Runners listed here will be available as self hosted
4
+# runners, configuration is directly pulled from the main branch.
5
+# runner_types:
6
+# runner_label:
7
+# instance_type: m4.large
8
+# os: linux
9
+# # min_available defaults to the global cfg in the ALI Terraform
10
+# min_available: undefined
11
+# # when max_available value is not defined, no max runners is enforced
12
+# max_available: undefined
13
+# disk_size: 50
14
+# is_ephemeral: true
15
+
16
+runner_types:
17
+ linux.2xlarge:
18
+ disk_size: 150
19
+ instance_type: c5.2xlarge
20
+ is_ephemeral: true
21
+ os: linux