Skip to content

Commit 1fa5cd1

Browse files
authored
Merge branch 'main' into feat/gpu-driver-auto-detect
2 parents b251078 + 78450b7 commit 1fa5cd1

4 files changed

Lines changed: 131 additions & 92 deletions

File tree

fern/docs.yml

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,10 @@ products:
3030
path: ../docs/index.yml
3131
slug: latest
3232
availability: stable
33+
- display-name: v0.17.0
34+
path: versions/v0.17.0.yml
35+
slug: v0.17.0
36+
availability: stable
3337
- display-name: v0.16.0
3438
path: versions/v0.16.0.yml
3539
slug: v0.16.0
@@ -38,10 +42,6 @@ products:
3842
path: versions/v0.15.0.yml
3943
slug: v0.15.0
4044
availability: stable
41-
- display-name: v0.14.0
42-
path: versions/v0.14.0.yml
43-
slug: v0.14.0
44-
availability: stable
4545
redirects:
4646
- source: "/aicr/index.html"
4747
destination: "/aicr/"

fern/versions/v0.14.0.yml

Lines changed: 0 additions & 84 deletions
This file was deleted.

fern/versions/v0.17.0.yml

Lines changed: 116 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,116 @@
1+
# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
navigation:
16+
- section: Overview
17+
contents:
18+
- page: Introduction
19+
path: v0.17.0-content/README.md
20+
21+
- section: User Guide
22+
contents:
23+
- page: Installation
24+
path: v0.17.0-content/user/installation.md
25+
- page: CLI Reference
26+
path: v0.17.0-content/user/cli-reference.md
27+
- page: CLI Configuration File
28+
path: v0.17.0-content/user/cli-config.md
29+
- page: Artifact Verification
30+
path: v0.17.0-content/user/artifact-verification.md
31+
- page: API Reference
32+
path: v0.17.0-content/user/api-reference.md
33+
- page: Agent Deployment
34+
path: v0.17.0-content/user/agent-deployment.md
35+
- page: Air-Gapped Mirroring
36+
path: v0.17.0-content/user/air-gap-mirror.md
37+
- page: Component Catalog
38+
path: v0.17.0-content/user/component-catalog.md
39+
- page: Recipe Health
40+
path: v0.17.0-content/user/recipe-health.md
41+
- page: TestGrid
42+
path: v0.17.0-content/user/testgrid.md
43+
- page: Validation
44+
path: v0.17.0-content/user/validation.md
45+
- page: Coverage Matrix
46+
path: v0.17.0-content/user/coverage-matrix.md
47+
48+
- section: Integrator Guide
49+
contents:
50+
- page: Automation
51+
path: v0.17.0-content/integrator/automation.md
52+
- page: Data Flow
53+
path: v0.17.0-content/integrator/data-flow.md
54+
- page: Kubernetes Deployment
55+
path: v0.17.0-content/integrator/kubernetes-deployment.md
56+
- page: AKS GPU Setup
57+
path: v0.17.0-content/integrator/aks-gpu-setup.md
58+
- page: EKS Dynamo Networking
59+
path: v0.17.0-content/integrator/eks-dynamo-networking.md
60+
- page: GKE TCPXO Networking
61+
path: v0.17.0-content/integrator/gke-tcpxo-networking.md
62+
- page: OpenShift Deployment
63+
path: v0.17.0-content/integrator/openshift.md
64+
- page: Talos Integration
65+
path: v0.17.0-content/integrator/talos-integration.md
66+
- page: Recipe Development
67+
path: v0.17.0-content/integrator/recipe-development.md
68+
- page: Data Extension
69+
path: v0.17.0-content/integrator/data-extension.md
70+
- page: Validator Extension
71+
path: v0.17.0-content/integrator/validator-extension.md
72+
- page: Supply Chain Verification
73+
path: v0.17.0-content/integrator/supply-chain-verification.md
74+
- page: Go Library Integration
75+
path: v0.17.0-content/integrator/go-library.md
76+
- page: Public API Surface
77+
path: v0.17.0-content/integrator/public-api.md
78+
- page: Measurement Schema
79+
path: v0.17.0-content/integrator/measurement-api.md
80+
- section: Components
81+
contents:
82+
- page: Nodewright
83+
path: v0.17.0-content/integrator/components/nodewright.md
84+
85+
- section: Contributor Guide
86+
contents:
87+
- page: Architecture Overview
88+
path: v0.17.0-content/contributor/index.md
89+
- page: Recipes, Overlays, and Mixins
90+
path: v0.17.0-content/contributor/recipe.md
91+
- page: Components
92+
path: v0.17.0-content/contributor/component.md
93+
- page: Collectors
94+
path: v0.17.0-content/contributor/collector.md
95+
- page: Validators
96+
path: v0.17.0-content/contributor/validator.md
97+
- page: Evidence Ingest
98+
path: v0.17.0-content/contributor/evidence-ingest.md
99+
- page: Inference-Perf Fluctuation (investigation)
100+
path: v0.17.0-content/contributor/inference-perf-fluctuation.md
101+
- page: CLI
102+
path: v0.17.0-content/contributor/cli.md
103+
- page: API Server
104+
path: v0.17.0-content/contributor/api-server.md
105+
- page: Testing
106+
path: v0.17.0-content/contributor/tests.md
107+
- page: Claude Skills
108+
path: v0.17.0-content/contributor/skills.md
109+
- page: Maintaining AICR
110+
path: v0.17.0-content/contributor/maintaining.md
111+
- page: Rekor v2 Signing
112+
path: v0.17.0-content/contributor/rekor-v2-signing.md
113+
- page: Publishing Recipe Evidence
114+
path: v0.17.0-content/contributor/evidence-publishing.md
115+
- page: UAT Day/Night Cycle
116+
path: v0.17.0-content/contributor/uat.md

recipes/components/nodewright-customizations/manifests/tuning.yaml

Lines changed: 11 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -126,10 +126,17 @@ spec:
126126
interrupt:
127127
type: reboot
128128
resources:
129-
cpuLimit: 4000m
130-
cpuRequest: 2000m
131-
memoryLimit: 8192Mi
132-
memoryRequest: 4096Mi
129+
# Elevated from 4000m/8192Mi for the EFA DKMS build. efa_installer.sh's
130+
# "Inspecting kernel" autoconf is a highly parallel kernel-module build;
131+
# inside the skyhook chroot nproc reports the host core count, so make -j
132+
# oversubscribes. Under the prior 4 CPU / 8Gi cgroup it was CFS-throttled
133+
# and its feature probes were starved/OOM-killed, so efa misdetected the
134+
# kernel and emitted compat shims that fail to compile on 6.17. More CPU
135+
# and memory headroom lets the probes complete and detect correctly.
136+
cpuLimit: 8000m
137+
cpuRequest: 4000m
138+
memoryLimit: 16384Mi
139+
memoryRequest: 8192Mi
133140
configMap:
134141
{{- if $cust.service }}
135142
service: {{ $cust.service }}

0 commit comments

Comments
 (0)