[CI] Shard chat APIs, model evals and model tests automatically (#61475)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com> Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
@@ -121,6 +121,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API chat_completion)"
|
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API chat_completion)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: entrypoints-integration-api-server-openai-chat_completion
|
key: entrypoints-integration-api-server-openai-chat_completion
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 83
|
timeout_in_minutes: 83
|
||||||
working_dir: "/vllm-workspace/tests"
|
working_dir: "/vllm-workspace/tests"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
|
|||||||
@@ -105,6 +105,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H100) LM Eval Large Models"
|
- label: ":nvidia: (H100) LM Eval Large Models"
|
||||||
key: lm-eval-large-models-4xh100
|
key: lm-eval-large-models-4xh100
|
||||||
|
automatic_shard: true
|
||||||
device: h100
|
device: h100
|
||||||
optional: true
|
optional: true
|
||||||
num_devices: 4
|
num_devices: 4
|
||||||
@@ -139,6 +140,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (B200) LM Eval Small Models"
|
- label: ":nvidia: (B200) LM Eval Small Models"
|
||||||
key: lm-eval-small-models-1xb200
|
key: lm-eval-small-models-1xb200
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 50
|
timeout_in_minutes: 50
|
||||||
device: b200-k8s
|
device: b200-k8s
|
||||||
optional: true
|
optional: true
|
||||||
|
|||||||
@@ -58,6 +58,7 @@ steps:
|
|||||||
- label: ":nvidia: (H200 MIG 35GB) Basic Models (Other)"
|
- label: ":nvidia: (H200 MIG 35GB) Basic Models (Other)"
|
||||||
device: h200_35gb
|
device: h200_35gb
|
||||||
key: basic-models-tests-other
|
key: basic-models-tests-other
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 38
|
timeout_in_minutes: 38
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/
|
||||||
|
|||||||
@@ -24,6 +24,7 @@ steps:
|
|||||||
|
|
||||||
- label: ":nvidia: (H200 MIG 18GB) Multimodal Models (Standard) 2: qwen3 + gemma"
|
- label: ":nvidia: (H200 MIG 18GB) Multimodal Models (Standard) 2: qwen3 + gemma"
|
||||||
key: multi-modal-models-standard-2-qwen3-gemma
|
key: multi-modal-models-standard-2-qwen3-gemma
|
||||||
|
automatic_shard: true
|
||||||
timeout_in_minutes: 75
|
timeout_in_minutes: 75
|
||||||
device: h200_18gb
|
device: h200_18gb
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
|
|||||||
Reference in New Issue
Block a user