Repository navigation
Conversation
Reuse pinned shared-cache snapshots and validate a loopback completion with\nschema-versioned JSON. Keep live serving distinct from offline fixtures. Signed-off-by: Doug Holt <dholt@nvidia.com>
Catch removed size, elapsed-time, generation-length and HTTP status guards. Clarify that the outer deadline must also cover shared-cache file reads. Signed-off-by: Doug Holt <dholt@nvidia.com>
Record GPT-2's MIT licence and vLLM's Apache-2.0 licence next to\nthe example pins, with revision-specific upstream sources. Co-Authored-By: Paperclip <noreply@paperclip.ing> Signed-off-by: Doug Holt <dholt@nvidia.com>
![github-code-quality[bot]](https://avatars.githubusercontent.com/u/9919?s=60&v=4){kind=small}
| time.sleep(drip_interval) | ||
| else: | ||
| self.wfile.write(data) | ||
| except (BrokenPipeError, ConnectionResetError): |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| time.sleep(drip_interval) | ||
| else: | ||
| self.wfile.write(data) | ||
| except (BrokenPipeError, ConnectionResetError): |
dholt
marked this pull request as ready for review
November 2, 2026 19:04
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Dependency
This change is stacked on the shared-model-cache branch. Review only the serving follow-on; merge the cache prerequisite first, preserving its original history.
Validation
ok=true, exit 0, exactly three requests. Missing weight file: JSONok=false, exit 1, no HTTP requests.Limits
No vLLM installation, real weights, live serving or GPU test was run for this change. Fixtures do not prove runtime compatibility, shared-storage behavior, read-only cache reuse or offline model loading. The validator cannot attest which revision the server loaded or whether it used a GPU. Those limits are explicit in the guide. Independent review of the exact head passed after the requested regression-test improvements. This is not a live-readiness claim.
No cluster defaults, deployment playbooks, driver settings or workflows change.