Restore authenticated HMA page deltas through SparkCache CUDA placement - #32
Closed
FujitsuPolycom wants to merge 4 commits into
Closed
Restore authenticated HMA page deltas through SparkCache CUDA placement#32FujitsuPolycom wants to merge 4 commits into
FujitsuPolycom wants to merge 4 commits into
Conversation
Use the direct-file native restore function only for immutable flat snapshot objects and route reconstructed page-delta bytes to the in-memory C++/CUDA page-placement function. The two interfaces have distinct verified signatures: direct restore accepts manifest lookup and cache-root inputs; page placement accepts authenticated encoded pages and a decoded page plan. A rejected page-delta restore continues to recompute rather than serving unverified state. SparkCache wire values, digest salts, chunk geometry, and cache namespace are unchanged; deployment source receipts are rebound to the resulting source tree. Validation: 739 SparkCache tests passed with 7 skipped; 108 deployment tests passed with 1 skipped; Ruff and diff checks passed.
Expose SparkCache CUDA restore and CUDA placement names in connector configuration, environment variables, deployment profiles, CLI options, logs, and documentation. Preserve legacy native-restore keys and Python symbols as compatibility aliases; conflicting canonical and legacy values reject startup and legacy-only input warns once per process. Cache identity, digest salts, chunk geometry, and stored bytes are unchanged. Validation: 746 SparkCache tests passed with 7 skipped; 108 deployment tests passed with 1 skipped; Ruff passed.
Page-semantic extensions accept authenticated chunk boundaries that fall inside a larger HMA page. The delta reuses only byte-identical page prefixes, so a changed boundary-intersecting page and every following page are immutable replacement data. This preserves the longest verified publication base instead of falling back to a full snapshot. Restore continues to authenticate the embedded base graph and reconstructed result before placement; invalid geometry or bytes remain a cache miss and recomputation. Canonical SparkCache CUDA restore and placement configuration remains the only generated configuration vocabulary. Deployable SparkCache source SHA-256: bc7cae86732c869ee8b2205d48ac5be6f580ee8b77a3e4ffd4c69dcd4f1bfae5. Cache namespace impact: none. CacheIdentity values, digest salts, chunk geometry, and page-delta wire schemas are unchanged. Validation: python -m pytest sparkcache -q (747 passed, 7 skipped); python -m pytest deploy -q (108 passed, 1 skipped); python -m ruff check .; source-attestation tests (2 passed).
FujitsuPolycom
force-pushed
the
codex/qualified-sparkcache-runtime
branch
from
August 30, 2026 05:50
4179714 to
5ec6a99
Compare
This was referenced Aug 30, 2026
Owner
Author
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
1 participant
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.
Resulting behavior
Status: implemented and qualified for the recorded GLM-5.3 TP4/DCP1 source deployment.
Authenticated hybrid-memory-allocator page deltas reconstruct a complete encoded page snapshot and send the verified bytes through SparkCache CUDA placement. A reusable prefix may end inside a larger allocator page: SparkCache retains earlier byte-identical pages and stores the boundary-intersecting page and all later pages as immutable replacements.
Page-delta descriptors are read and verified with a bounded eight-worker pool while preserving manifest order. Canonical SparkCache CUDA configuration names are used throughout deployment profiles and runtime messages. Legacy configuration names and Python imports remain compatibility interfaces.
If identity, compatibility, descriptor integrity, reconstructed-page integrity, or placement cannot be verified, SparkCache rejects the stored state and vLLM recomputes the request.
Compatibility
Cache identity values, digest salts, 256-token logical geometry, on-disk schemas, and the placement C ABI are unchanged. Cache namespace impact: none. Existing compatible entries remain readable.
Validation
This PR consolidates the implemented behavior previously presented in draft PRs #25, #26, #29, and #30. Those drafts remain open until this consolidation is reviewed.