Skip to content

[rhaiis] Add custom model and workload stubs for dashboard overrides #179

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Harshith-umesh merged 2 commits into from
Aug 21, 2026
+26 −5
Merged

[rhaiis] Add custom model and workload stubs for dashboard overrides #179

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b70d81c
feat: add custom model and workload stubs for dashboard
sacherukuri Aug 19, 2026
566c536
feat: enable rhaiis agentic failure review.
sacherukuri Aug 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions projects/rhaiis/orchestration/config.d/models.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,13 @@ qwen3-0_6b:
vllm_args:
tensor-parallel-size: 1

# Dashboard override stub (set hf_model_id and vllm_args at runtime)
custom:
name: custom
hf_model_id: ""
vllm_args:
tensor-parallel-size: 1

# Llama-4 Scout (MoE)
llama-4-scout:
name: Llama-4-Scout-17B-16E-Instruct
Expand Down
9 changes: 5 additions & 4 deletions projects/rhaiis/orchestration/config.d/workloads.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,25 +7,21 @@ profile1:
data: "prompt_tokens=1000,output_tokens=1000"
rates: [1,50,100,200,300]
max_seconds: 450
rampup: 10

profile2:
data: "prompt_tokens=512,prompt_tokens_stdev=128,prompt_tokens_min=1,prompt_tokens_max=1024,output_tokens=2048,output_tokens_stdev=512,output_tokens_min=1,output_tokens_max=4096"
rates: [1,50,100,200,300]
max_seconds: 450
rampup: 10

profile3:
data: "prompt_tokens=2048,output_tokens=128"
rates: [1, 50, 100, 200, 300]
max_seconds: 450
rampup: 10

profile4:
data: "prompt_tokens=8000,output_tokens=1000"
rates: [1,25,50,75,100]
max_seconds: 450
rampup: 10
samples: 50

profile5:
Expand All @@ -44,3 +40,8 @@ profile7:
rates: [1, 50, 100, 200, 300]
max_seconds: 450

# Dashboard override stub (set data, rates, max_seconds at runtime)
custom:
data: "prompt_tokens=1000,output_tokens=1000"
rates: [1]
max_seconds: 450
6 changes: 6 additions & 0 deletions projects/rhaiis/orchestration/presets.d/presets.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,12 @@ profile6:
profile7:
tests.rhaiis.workload_key: profile7

custom:

@Harshith-umesh Harshith-umesh Aug 20, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

these presets are not required.

tests.rhaiis.model_key: custom

custom-profile:
tests.rhaiis.workload_key: custom

# ── Models ──────────────────────────────────────────────────
# Short aliases default to the FP8 variant where available.
# Use the full name (e.g. llama-70b-w4a16) for other quants.
Expand Down
Loading