feat(runtime): add dormant Podman GPU and local inference by ericksoa · Pull Request #8061 · NVIDIA/NemoClaw

ericksoa · 2026-08-01T13:39:32Z

Summary

Adds the dormant provider-owned Podman GPU and host-local inference layer for Ollama, NVIDIA NIM, and vLLM. OpenClaw, Hermes, and LangChain Deep Agents Code consume the same provider-neutral routing contract. Podman remains absent from production registration, and Dockerfile onboarding remains the default.

Related Issue

Part of #7744.

Changes

Translate generic GPU requests into Podman/CDI arguments after exact preflight inventory and persist selected GPU authority.
Add credential-safe Ollama, NIM, and vLLM command construction, startup, inspection, readiness, restart, stop, preservation, and receipts.
Route host-local inference through the runtime-provider bundle without central Podman switches.
Wire the dormant provider contract for OpenClaw, Hermes, and LangChain Deep Agents Code.
Preserve the MXC-style seam with explicit unsupported host-local inference.
Keep hidden --temp-managed-runtime default-off and undocumented; this slice does not register or activate Podman.

Type of Change

Code change

Quality Gates

Tests added or updated
Public docs not applicable because the provider remains dormant and the temporary gate is intentionally undocumented
Sensitive paths changed
Provider-neutral source-shape and credential-safe argv/receipt tests accompany the implementation
Source PR CodeRabbit audit found zero unresolved threads

Documentation Writer Review

Documentation writer subagent reviewed the completed changes
Result: no-docs-needed
Evidence: This patch adds dormant provider-owned Podman GPU and host-local Ollama, NIM, and vLLM contracts and routing for OpenClaw, Hermes, and LangChain Deep Agents Code. Podman remains absent from the production provider registry, MXC host-local inference remains explicitly unsupported, and no supported workflow is activated. The existing hidden, default-off --temp-managed-runtime flag remains intentionally undocumented.
Agent: Codex Desktop

Verification

Signed commits and DCO
197 changed runtime-provider tests plus 65 focused MXC/provider/source tests passed locally before the wording-only follow-up
50 affected tests, CLI typecheck, and test-conditional scan passed after the wording and assertion follow-ups
Repository, source-shape, test-size, secret, commit, and pre-push gates passed
Exact-head GitHub qualification is running

Exact head: 5d5566154c7c.
Exact public delta before the five-file wording follow-up: 31 files, +3,032/-14.

Signed-off-by: Aaron Erickson aerickson@nvidia.com

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

coderabbitai · 2026-08-01T13:39:42Z

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 6622ca4b-92cc-44f9-8f01-b82eb0f9372b

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

_{Comment @coderabbitai help to get the list of available commands.}

github-code-quality · 2026-08-01T13:40:17Z

Code Coverage Overview

Languages: TypeScript

TypeScript / code-coverage/plugin

The overall coverage in commit 5d55661 in the feat/podman-host-loc... branch remains at 96%, unchanged from commit a82887e in the feat/persisted-engin... branch.

TypeScript / code-coverage/cli

The overall coverage in commit 5d55661 in the feat/podman-host-loc... branch remains at 81%, unchanged from commit a82887e in the feat/persisted-engin... branch.

Show a code coverage summary of the most impacted files.

File	`feat/persisted-engin...` a82887e	`feat/podman-host-loc...` 5d55661	+/-
`src/lib/onboard...strap/docker.ts`	69%	60%	-9%
`src/lib/onboard...atcher-lease.ts`	0%	75%	+75%
`src/lib/onboard...ne-lifecycle.ts`	0%	83%	+83%
`src/lib/onboard...al-inference.ts`	0%	85%	+85%
`src/lib/onboard...trap-journal.ts`	0%	86%	+86%
`src/lib/onboard...-replacement.ts`	0%	88%	+88%
`src/lib/onboard...-transaction.ts`	0%	88%	+88%
`src/lib/onboard...eld-workload.ts`	0%	88%	+88%
`src/lib/onboard...ne-authority.ts`	0%	91%	+91%
`src/lib/onboard...ate-mutation.ts`	0%	93%	+93%

_{Updated August 05, 2026 10:01 UTC}

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

github-actions · 2026-08-01T13:44:42Z

PR Review Advisor — No blocking findings reported

Advisor assessment: No blocking advisor findings reported
Next action: Review the warnings below.
Findings: 0 blockers · 1 warning · 0 suggestions

Model lanes

GPT-5.6 Terra (primary): Completed · high confidence · 0 blockers · 1 warning · 0 suggestions
Nemotron 3 Ultra (second opinion): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
Model comparison: normalized findings differ; normalized terminology decisions differ; normalized E2E selections match; Nemotron reported the same number of blockers, 1 fewer warning, the same number of suggestions.

8 terminology differences from the second opinion

Advisory only. These are normalized differences from the primary terminology receipt.

host-local inference at src/lib/onboard/runtime-provider/host-local-inference.ts:67: primary classified it as established; the second opinion classified it as define.
inference.local at src/lib/onboard/runtime-provider/host-local-inference-routing.ts:13: selected only by the second-opinion lane as established.
engine authority at src/lib/onboard/runtime-provider/host-local-inference.ts:239: selected only by the second-opinion lane as established.
host.openshell.internal at src/lib/onboard/runtime-provider/host-local-inference-routing.ts:12: selected only by the second-opinion lane as established.
host.containers.internal at src/lib/onboard/runtime-provider/podman-host-local-inference.ts:42: selected only by the second-opinion lane as established.
CDI device at src/lib/onboard/runtime-provider/podman-gpu.ts:14: selected only by the second-opinion lane as established.
provider-owned at src/lib/onboard/runtime-provider/host-local-inference.ts:58: selected only by the second-opinion lane as established.
route authority at src/lib/onboard/runtime-provider/podman-host-local-inference.ts:271: selected only by the second-opinion lane as define.

Second-opinion terminology and E2E selections are advisory. They do not change the primary assessment or E2E / PR Gate.

3 semantic terminology decisions

Terminology decisions are advisory. They affect the assessment only when a separate finding identifies concrete semantic impact.

established — host-local inference at src/lib/onboard/runtime-provider/host-local-inference.ts:67: Use host-local inference consistently for the provider operation and receipt contract.
established — provider-owned at src/lib/onboard/runtime-provider/host-local-inference.ts:95: Retain provider-owned where the provider, rather than central orchestration, controls the named authority or lifecycle.
justified — provider-neutral at src/lib/onboard/runtime-provider/host-local-inference-routing.test.ts:81: Retain provider-neutral for the injected-runtime routing contract; the test demonstrates the concrete contrast.

E2E guidance

Advisory only. E2E / PR Gate selects and runs jobs independently.

Recommended E2E: cloud-onboard, inference-routing, network-policy, onboard-repair, onboard-resume

1 warning · 0 suggestions

Warnings

Warnings do not block.

`PRA-1` Warning — Host-local inference surface has no production request path

Location: src/lib/onboard/machine/handlers/provider-inference.ts:71
Category: scope
Problem: The new hostLocalInference option is declared but is not propagated by either production setupInference call. The only checked-in callers that supply it are direct setupInference tests.
Impact: Normal onboarding cannot activate the new provider-owned host-local inference path, so the added Podman runtime and routing surface remains unreachable from its intended flow.
Recommendation: Either propagate a provider-owned hostLocalInference request from the current onboarding selection path, or remove the dormant activation surface until that consumer lands.
Verification: Inspect both deps.setupInference calls near lines 809 and 1012 and search production sources for hostLocalInference; neither call adds the option.
Test coverage: Add an onboarding-state test that selects a host-local service and proves provider-inference passes the exact request to setupInference, which then starts the provider runtime before gateway registration.
Evidence: src/lib/onboard/machine/handlers/provider-inference.ts:71 declares ProviderInferenceSetupOptions.hostLocalInference. src/lib/onboard/machine/handlers/provider-inference.ts:809 and :1012 call deps.setupInference with inferenceOptions that never includes hostLocalInference. The production-source search finds hostLocalInference only in setup-inference.ts and runtime-provider code; test/onboard-host-local-inference-routing.test.ts supplies it directly.

Workflow run details

This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge.

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

apurvvkumaria

Comment — reviewed exact head 303387b. The provider is dormant and existing Docker vLLM profiles already rely on host IPC, so I found no blocking defect in the current change. Non-blocking fast follow before activation: assess whether private IPC plus explicit shared-memory sizing can replace ipc: host, which currently emits --ipc=host and broadens the container boundary. Exact-head core CI is green.

## Summary This PR adds the dormant Podman GPU-qualification and inference-command translation boundary for the incremental runtime stack in #7744. It does not register Podman for production selection or advertise user-visible Podman support. ## Changes - Add an operation-scoped `host-local-inference` engine contract so runtime providers can request GPU-qualified execution without a Podman switch in central orchestration. Provider contract and source-shape tests protect this boundary. - Record the exact Podman authority and qualified CDI device inventory during preflight. Qualification now preserves the raw inventory through validation and fails closed on both exact and normalization-equivalent duplicate device identities before any deduplication can hide them. - Translate Docker-compatible inference GPU arguments into Podman CDI device arguments. Unit tests cover `all`, indexed GPUs, GPU UUIDs, MIG devices, container-name filters, and fail-closed rejection of unsupported NVIDIA runtime, duplicate, unqualified, or raw-device options. - Keep the new path dormant. Production provider selection, agent behavior, Docker behavior, and Kubernetes behavior do not change in this slice. ## Advisor disposition - The duplicate-CDI fail-closed finding is fixed at exact head `e74e262c2`; the denial test supplies the same canonical CDI identity from both endpoint inventory and the separately qualified inventory and proves qualification rejects it. - The dormant-translator suggestion is intentionally not applied in this slice. Epic #7744 defines this review unit as the inert GPU/translation contract; stacked PR #8061 supplies its named, operation-scoped host-local inference provider consumer. Production activation remains owned by the later qualification slice after every agent, GPU/local inference path, recovery path, and protected E2E pass. Removing the contract here or adding a central Podman switch would defeat that incremental, pluggable stack design. ## Type of Change - [x] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Quality Gates - [x] Tests added or updated for changed behavior - [ ] Existing tests cover changed behavior — justification: - [ ] Tests not applicable — justification: - [ ] Docs updated for user-facing behavior changes - [x] Docs not applicable — justification: This slice adds an internal, dormant provider contract and does not activate or document a supported surface. - [x] Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging) - [x] Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification: Independent exact-head review verified fail-closed CDI identity, endpoint authority, provider-neutral operation scope, and dormant production selection. - [ ] Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue: ## Advisor Disposition - Earlier PRA-1, which found duplicate CDI identities lost before normalization, is resolved by d4622df. Endpoint-reported and additional identities now remain in one raw array until normalizePodmanCdiInventory rejects normalized duplicates; the focused test covers both prefixed and shorthand collisions. - Earlier PRA-2, now published as the PRA-1 dormant-consumer suggestion, is explicitly retained for the maintainer-approved incremental stack. Wiring production here would violate the dormant review thesis for this slice and bypass the receipt authority that lands in #8060. Stacked #8061 is the named production-bound provider consumer and adds provider-level contract tests for qualified CDI devices. Current central selection still excludes Podman, and the source-shape test rejects Podman switches in central orchestration. ## Documentation Writer Review - [x] Documentation writer subagent reviewed the completed changes - Result: `no-docs-needed` - Evidence: Independent review of the exact 13-file slice at e74e262 against base baa495a, WRITING.md, the controlled word list, and docs/CONTRIBUTING.md found no documentation update required. CURRENT_RUNTIME_PROVIDER_BUNDLES still contains only Docker and Kubernetes, the Podman provider still reports hostLocalInference false, and user-visible Podman support remains inactive. The duplicate-CDI repair collects endpoint and additional device identities before normalization and rejects normalized duplicates. Stable patch ID 681a1e01ee7d6328fef26c359ef7b75b88301c9e and binary diff SHA-256 4fc440a2a439e604553eb24aba928dbd507ec5558cfa8d31383795c49eb4098d bind the receipt. CLI build and typecheck, 97 focused CLI tests, 2 source-shape tests, repository checks, and git diff --check passed. - Agent: Codex Desktop   ## DGX Station Hardware Evidence - [ ] Tested on DGX Station - Tested commit: Not applicable; this slice remains dormant and protected runtime qualification is owned by the activation slice. - Station profile/scenario: Not applicable. - Result: Not applicable. - Supporting evidence: Not applicable. ## Verification - [x] PR description includes a `Signed-off-by:` line and every commit appears as `Verified` in GitHub - [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or `npm run validate:pr` passed after refreshing `origin/main` when hooks were skipped or unavailable - [x] Targeted behavior tests pass for the current change set, or tests are marked not applicable above — command/result or justification: At exact head e74e262 on base baa495a, six focused CLI files passed 97 tests; the runtime-provider source-shape file passed 2 tests; npm run build:cli, npm run typecheck:cli, npm run checks:repository, and git diff --check passed. - [ ] Applicable broad gate passed — `npm test` for broad runtime/test-harness changes; `npm run check` for repo-wide validation/coverage changes — command/result: Exact-head CI and protected E2E are running. - [x] Quality Gates section completed with required justifications or waivers - [x] No secrets, API keys, or credentials committed - [ ] `npm run docs` builds without warnings (doc changes only) - [ ] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) --- Signed-off-by: Aaron Erickson <aerickson@nvidia.com> --------- Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

## Summary This PR adds a provider-neutral durable receipt contract for host-local Ollama, NVIDIA NIM, and vLLM inference. The contract remains dormant and does not activate Podman or any user-visible inference path. ## Changes - Define provider-neutral endpoint and runtime-authority receipt variants for host-process Ollama and managed-container NIM/vLLM services. - Bind every receipt to persisted engine authority, provider identity, exact endpoint/network authority, and immutable runtime proof. - Require digest-pinned OCI images, normalized NVIDIA CDI device inventory, and a secret-free managed-container specification digest. - Add canonical parse and serialization rules that reject authority drift, mutable image references, malformed devices, invalid endpoints, unsupported fields, and noncanonical persisted data. - Demonstrate through an MXC-style fixture that another provider can produce valid receipts without Podman-specific orchestration or central switches. The lifecycle command interface and provider implementation intentionally remain outside this receipt-only slice. They are introduced with their first consumer in stacked PR #8061. ## Type of Change - [x] Code change (feature, bug fix, or refactor) - [ ] Code change with doc updates - [ ] Doc only (prose changes, no code sample modifications) - [ ] Doc only (includes code sample changes) ## Quality Gates - [x] Tests added or updated for changed behavior - [ ] Existing tests cover changed behavior — justification: - [ ] Tests not applicable — justification: - [ ] Docs updated for user-facing behavior changes - [x] Docs not applicable — justification: This slice defines a dormant internal persistence contract and activates no supported runtime or inference surface. - [x] Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging) - [x] Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification: Independent exact-head review verified strict authority normalization, canonical parsing, immutable image/device proof, and the dormant boundary on `4b75eb4af615060a535c9354f17096109fa2fa93`. - [ ] Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue: ## Documentation Writer Review - [x] Documentation writer subagent reviewed the completed changes - Result: `no-docs-needed` - Evidence: Exact-head review found no user-facing behavior, command, configuration, or supported-runtime activation to document in this receipt-only slice. - Agent: Codex Desktop   ## DGX Station Hardware Evidence - [ ] Tested on DGX Station - Tested commit: - Station profile/scenario: - Result: - Supporting evidence: ## Verification - [x] PR description includes a `Signed-off-by:` line and every commit appears as `Verified` in GitHub - [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or `npm run validate:pr` passed after refreshing `origin/main` when hooks were skipped or unavailable - [x] Targeted behavior tests pass for the current change set, or tests are marked not applicable above — command/result or justification: `npm test -- --run src/lib/onboard/runtime-provider/host-local-inference.test.ts test/runtime-provider-source-shape.test.ts` passed 9/9 tests on `4b75eb4af615060a535c9354f17096109fa2fa93`. - [x] Applicable broad gate passed — `npm run build:cli`, `npm run typecheck:cli`, and `npm run checks:repository` passed on the exact head. - [x] Quality Gates section completed with required justifications or waivers - [x] No secrets, API keys, or credentials committed - [ ] `npm run docs` builds without warnings (doc changes only) - [ ] Doc pages follow the [style guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md) (doc changes only) - [ ] New doc pages include SPDX header and frontmatter (new pages only) ## Exact Slice Identity - Head: `4b75eb4af615060a535c9354f17096109fa2fa93` - Base: `e74e262c28f514bc9e782b157c2c2549a710ad8c` - Stable patch ID: `1def8b6763adaaf86faec8bc90f60184fbf9dbd2` - Binary diff SHA256: `e03b55f97e2f5f713252106de7f04320353345dd08c9d4464f1664c7e18ea5e3` - Scope: 3 files, 357 additions, 0 deletions ## Advisor Disposition - The exact-head Nemotron lane completed with zero blockers, warnings, or suggestions. - The exact-head Terra lane failed its response-schema check and published no substantive finding; this is an advisor execution failure, not a code finding. - The earlier valid architecture concern about an unconsumed lifecycle interface is resolved on this head: the interface and command DTOs were removed from #8060 and moved to #8061, where the Podman implementation consumes them. --- Signed-off-by: Aaron Erickson <aerickson@nvidia.com> --------- Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

cv

Reviewed commit 303387bddf in bottom-up stack order. This PR depends on #8058, which is not approval-ready. The Podman inference layer conflicts with its parent and lacks passing current compliance and E2E evidence. Review remains blocked until the parent is reconstructed or repaired, this branch is restacked on the accepted parent commit, and current CI, security, and documentation evidence passes for the resulting commit. No approval is granted for the current branch.

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

copy-pr-bot · 2026-08-05T09:33:24Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

ericksoa added 15 commits August 1, 2026 05:24

feat(runtime): qualify Podman inference GPUs

cfa7cbb

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh persisted engine lifecycle

02b7389

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

feat(runtime): translate Podman inference commands

d11f708

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh persisted engine lifecycle parent

1d2a111

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

feat(runtime): define host-local inference receipts

9d8fee1

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh persisted engine lifecycle parent

bff34f9

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh Podman inference parent

eb88cce

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

feat(runtime): bind host-local inference specifications

6c23ebd

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

feat(runtime): manage Podman host-local inference

54cc06f

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh persisted engine lifecycle parent

32751f3

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh Podman inference parent

ee6ad30

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh host-local inference receipt parent

333aab6

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

feat(runtime): expose host-local inference providers

4c66a17

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

test(runtime): complete provider surface fixture

ec453b7

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

chore(runtime): format host-local inference slice

1add3cc

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

ericksoa self-assigned this Aug 1, 2026

fix(runtime): reject duplicate Podman CDI inventory

d4622df

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

github-advanced-security AI found potential problems Aug 1, 2026

View reviewed changes

Comment thread src/lib/onboard/runtime-provider/podman-host-local-inference.test.ts Fixed

ericksoa added 4 commits August 1, 2026 07:09

merge(stack): refresh persisted engine lifecycle parent

e74e262

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

test(runtime): linearize Podman inference harness

3ef4794

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh Podman GPU translation parent

f4628d3

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): refresh host-local inference receipt parent

3485901

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

This was referenced Aug 1, 2026

[Epic] Support native Podman with buildless managed onboarding #7744

Open

feat(runtime): qualify Podman inference commands #8059

Merged

github-advanced-security AI found potential problems Aug 1, 2026

View reviewed changes

Comment thread src/lib/onboard/runtime-provider/podman-host-local-inference.test.ts Fixed

ericksoa added 2 commits August 1, 2026 07:27

refactor(runtime): keep receipt slice domain-only

4b75eb4

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): narrow host-local inference receipt parent

e2c5a19

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

ericksoa added 5 commits August 2, 2026 07:07

merge(stack): restack routing on test-only harness

d62c13b

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

fix(runtime): reprove managed inference readiness

303387b

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): restack routing on managed readiness

38f670e

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

test(runtime): carry managed readiness authority

68991cc

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

test(runtime): cover managed route retry

b588f8b

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

apurvvkumaria reviewed Aug 3, 2026

View reviewed changes

Base automatically changed from feat/host-local-inference-receipts to feat/persisted-engine-lifecycle August 3, 2026 23:41

jyaunches mentioned this pull request Aug 4, 2026

feat(runtime): define provider state-mutation contract #8186

Closed

23 tasks

cv reviewed Aug 4, 2026

View reviewed changes

cv mentioned this pull request Aug 4, 2026

feat(runtime): route host-local inference #8066

Merged

9 tasks

ericksoa added 2 commits August 4, 2026 22:46

merge(stack): rebuild Podman GPU and inference runtime

a84e56c

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): integrate host-local inference routing

1539456

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

ericksoa changed the title ~~feat(runtime): manage Podman host-local inference~~ feat(runtime): add dormant Podman GPU and local inference Aug 5, 2026

ericksoa added 3 commits August 5, 2026 00:00

merge(stack): absorb persisted lifecycle batch

d5159f4

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

merge(stack): reconcile host inference with MXC

f046d6e

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

docs(runtime): clarify dormant Podman contracts

c1d6087

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

test(runtime): align Podman CDI diagnostic

5d55661

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>

ericksoa added the v0.0.104 Release target label Aug 5, 2026

ericksoa mentioned this pull request Aug 5, 2026

[Managed inference] Bind verified llama.cpp artifact into durable lifecycle #8395

Closed

9 tasks

Navigation Menu

Uh oh!

feat(runtime): add dormant Podman GPU and local inference - #8061

feat(runtime): add dormant Podman GPU and local inference#8061
ericksoa wants to merge 42 commits into
feat/persisted-engine-lifecyclefrom
feat/podman-host-local-inference-runtime

ericksoa commented Aug 1, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot commented Aug 1, 2026 •

edited

Loading

Review skipped

Uh oh!

github-code-quality Bot commented Aug 1, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Aug 1, 2026 •

edited

Loading

Warnings

`PRA-1` Warning — Host-local inference surface has no production request path

Uh oh!

Uh oh!

Uh oh!

apurvvkumaria left a comment

Uh oh!

cv left a comment

Uh oh!

copy-pr-bot Bot commented Aug 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Uh oh!

Conversation

ericksoa commented Aug 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Related Issue

Changes

Type of Change

Quality Gates

Documentation Writer Review

Verification

Uh oh!

coderabbitai Bot commented Aug 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

github-code-quality Bot commented Aug 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Coverage Overview

TypeScript / code-coverage/plugin

TypeScript / code-coverage/cli

Uh oh!

github-actions Bot commented Aug 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

PR Review Advisor — No blocking findings reported

Model lanes

E2E guidance

Warnings

PRA-1 Warning — Host-local inference surface has no production request path

Uh oh!

Uh oh!

Uh oh!

apurvvkumaria left a comment

Choose a reason for hiding this comment

Uh oh!

cv left a comment

Choose a reason for hiding this comment

Uh oh!

copy-pr-bot Bot commented Aug 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

ericksoa commented Aug 1, 2026 •

edited

Loading

coderabbitai Bot commented Aug 1, 2026 •

edited

Loading

github-code-quality Bot commented Aug 1, 2026 •

edited

Loading

github-actions Bot commented Aug 1, 2026 •

edited

Loading

`PRA-1` Warning — Host-local inference surface has no production request path