Skip to content

test(inference): activate OpenClaw llama.cpp qualification #8579

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
cv merged 1 commit into from
Aug 7, 2026
Merged

test(inference): activate OpenClaw llama.cpp qualification #8579

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion managed-inference/qualifications/llama-cpp.openclaw.spark-single.v1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ metadata:
id: llama-cpp.openclaw.spark-single.v1

spec:
execution: disabled
execution: enabled
agent: openclaw
image:
reference: ghcr.io/nvidia/nemoclaw/openclaw-sandbox@sha256:3648441718cdd6c2bc4c8fe39fa0d04d3931656b2063af34215cc51841cd0d5e
Expand Down
5 changes: 3 additions & 2 deletions test/llama-cpp-dgx-spark-qualification-plan.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ describe("llama.cpp DGX Spark qualification plan export (#8260)", () => {
);

expect(output.execution).toBe("enabled");
expect(output.agent_qualification_execution).toBe("disabled");
expect(output.agent_qualification_execution).toBe("enabled");
expect(output.runner).toBe("linux-arm64-gpu-dgx-spark-gb10-protected-1");
expect(parseLlamaCppDgxSparkQualificationPlan(JSON.parse(output.qualification))).toMatchObject({
execution: "enabled",
Expand All @@ -112,7 +112,7 @@ describe("llama.cpp DGX Spark qualification plan export (#8260)", () => {
qualification: {
agentQualification: {
agent: "openclaw",
execution: "disabled",
execution: "enabled",
runtimeProvider: "docker",
},
probeBounds: {
Expand Down Expand Up @@ -146,6 +146,7 @@ describe("llama.cpp DGX Spark qualification plan export (#8260)", () => {
const output = exportLlamaCppDgxSparkQualificationPlan(repoRoot);

expect(output).toMatchObject({
agent_qualification_execution: "enabled",
environment: "approve-dgx-spark-image-qualification",
execution: "enabled",
model_host_path: "/var/lib/nemoclaw/models/Nemotron-3-Nano-30B-A3B-UD-Q4_K_XL.gguf",
Expand Down
4 changes: 2 additions & 2 deletions test/llama-cpp-image.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,7 @@ describe("declarative llama.cpp server image", () => {
},
qualification: {
agentQualification: {
execution: "disabled",
execution: "enabled",
image: {
reference:
"ghcr.io/nvidia/nemoclaw/openclaw-sandbox@sha256:3648441718cdd6c2bc4c8fe39fa0d04d3931656b2063af34215cc51841cd0d5e",
Expand Down Expand Up @@ -445,7 +445,7 @@ describe("declarative llama.cpp server image", () => {
manifestSource,
recipeSource,
undefined,
qualificationSource.replace("execution: disabled", "execution: enabled"),
qualificationSource,
);

expect(JSON.parse(enabled.publication_qualification_plan)).toMatchObject({
Expand Down
Loading