[AQUA][GPT-OSS] Add Shape-Specific Env Config for GPT-OSS Models in AQUA Deployment Config Reader #1244
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mrDzurb
requested review from
darenr,
mayoor,
VipulMascarenhas,
qiuosier and
ahosler
as code owners
oracle-contributor-agreement
bot
added
the
OCA Verified
darenr
previously approved these changes
Aug 10, 2025
|
📌 Cov diff with main: 📌 Overall coverage: |
|
📌 Cov diff with main: 📌 Overall coverage: |
mayoor
reviewed
Aug 10, 2025
ads/aqua/common/utils.py
Outdated
| @@ -997,6 +997,45 @@ def get_container_params_type(container_type_name: str) -> str: | |||
| return UNKNOWN | |||
|
|
|||
|
|
|||
| @lru_cache(maxsize=None) | |||
There was a problem hiding this comment.
we need expiration, otherwise if there is an update to the config, it might no reflect
mayoor
approved these changes
Aug 10, 2025
darenr
approved these changes
Aug 10, 2025
|
📌 Cov diff with main: 📌 Overall coverage: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description:
Summary
This PR updates the AQUA deployment config reader to support shape-specific environment variables for GPT-OSS model deployments. The change introduces an
envsection in the deployment configuration for A-series GPU shapes, allowing AQUA handlers to return custom environment variables alongside existing parameter sets.Example
A request to:
will now return:
{ "data": [ "--trust-remote-code", "--gpu-memory-utilization 0.98", "--enforce-eager", "--max-num-seqs 32", "--max_model_len 130000", "--dtype bfloat16" ], "env": { "VLLM_ATTENTION_BACKEND": "TRITON_ATTN_VLLM_V1" } }This change is required to ensure GPT-OSS model deployments on A-series shapes use the correct VLLM attention backend (
TRITON_ATTN_VLLM_V1), which improves compatibility and performance for these hardware configurations.