[CI] Enroll a third batch of five steps in automatic sharding (#60757)

Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Thang Nguyen
2026-10-09 03:26:47 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent b8bd335754
commit efd141047d
5 changed files with 5 additions and 0 deletions
+1
View File
@@ -33,6 +33,7 @@ steps:
- label: ":nvidia: (H200 MIG 18GB) CUDAGraph"
device: h200_18gb
key: cudagraph
automatic_shard: true
timeout_in_minutes: 45
source_file_dependencies:
- tests/v1/cudagraph
+1
View File
@@ -38,6 +38,7 @@ steps:
- label: ":nvidia: (L4) V1 Engine"
key: engine-1-gpu
automatic_shard: true
device: l4
num_devices: 1
timeout_in_minutes: 45
+1
View File
@@ -5,6 +5,7 @@ steps:
- label: ":nvidia: (H200 MIG 35GB) LM Eval Small Models"
device: h200_35gb
key: lm-eval-small-models
automatic_shard: true
timeout_in_minutes: 45
source_file_dependencies:
- csrc/
+1
View File
@@ -4,6 +4,7 @@ depends_on:
steps:
- label: ":nvidia: (H200 MIG 18GB) V1 Sample"
key: v1-sample
automatic_shard: true
timeout_in_minutes: 45
device: h200_18gb
source_file_dependencies: &v1-sample-logits-deps
+1
View File
@@ -80,6 +80,7 @@ steps:
- label: ":nvidia: (B200) Quantized MoE"
key: quantized-moe-test-b200
automatic_shard: true
timeout_in_minutes: 120
working_dir: "/vllm-workspace/"
device: b200-k8s