Skip to content

fix[notask]: integrate tiled-image geometry and resize rounding fixes - #5489

Open
DmitryMalishev wants to merge 17 commits into
mainfrom
codex/llm-media-runtime-validation
Open

DmitryMalishev wants to merge 17 commits into
mainfrom
codex/llm-media-runtime-validation

Conversation

@DmitryMalishev

@DmitryMalishev DmitryMalishev commented Oct 30, 2026 •

Copy link
Copy Markdown
Contributor

Task: QVAC-27614

🎯 What problem does this PR solve?

  • Issue 2 — Cached tiled-image geometry is lost. Valid tiled server requests can fail because serialized image chunks lose their grid dimensions. Fabric #457 fixes serialization; this PR integrates that engine for end-to-end validation.
  • Issue 12 — Image resize rounding differs from the reference processor. Half-way dimensions can add an image-token row or column. Fabric #457 fixes rounding; this PR adds addon-level boundary coverage.
  • Issue 3 — Missing SDK completion stop reasons is addressed independently in #5516.

📝 How does it solve it?

  • Pin the temporary packages/fabric vcpkg overlay to Fabric 4fe4ded8519d4ce4ce241fe6b73594545253025e, with a verified source SHA-512.
  • After updating from main, refresh the overlay to the registry's 11259.2.0#2 recipe and helpers. Keep that recipe's CUDA runtime isolation and module-symbol checks; change only its source REF/checksum. This preserves the runtime corrections now required by main, including #5460.
  • Extend the existing Qwen3.5 image test: 464 pixels rounds to 448, 496 to 512, and the aligned intermediate size retains its extra token row. Existing tile-mode assertions remain.
  • Retain the separate test-maintenance correction for CPU-only translation runners: verify the precise unavailable-device error while keeping all device/status assertions when a GPU is available.
  • Keep fixture provisioning out of this PR: the sharded embedding fixture repair is being handled separately. The original Hugging Face URL returns HTTP 401 before model loading. Automatic PR CI reads its staging list from main, so the earlier staging-list change in this branch could not take effect; that ineffective change has been removed.

🧪 How was it tested?

  • Current head 32472534a includes main 69a8cd98c. LLM JavaScript unit tests, fixture/helper tests, mobile configuration validators, lint, type checks and consumer type checks passed locally; lint reports three existing require-await warnings.
  • All 37 local runtime-symbol and Fabric-overlay policy tests passed. The shell-based dispatch tests could not run locally without Bash/jq; the Linux CI policy suite passed.
  • Verified the overlay matches the registry add public reusable for qvac-cli #2 port structurally, including both helper files, with only the intended source pin/checksum changed. Public diffs were checked for confidential identifiers.
  • All nine refreshed Fabric platform prebuilds passed. Consumer smoke checks are still running in the Fabric matrix and cross-addon desktop/native CI are running. The known HF fixture failure is reported separately; every other check must pass before review readiness is claimed.
  • Previous head 2b6c46f47: all nine Fabric prebuilds and consumer smoke checks passed. All LLM C++/desktop integration checks and the CPU-only translation rows passed. Seven embedding integration jobs failed before model loading because the original fixture URL returned HTTP 401; their logs show only the old staging list. This is a confirmed external fixture failure, independent of the native fixes.
  • Earlier GPU validation against Fabric 4fe4ded85 passed all three mtmd test targets, 100 sequential server requests, 14 batched controls, four CPU grid cases, two resize-boundary requests, 14 addon assertions and 13 SDK stop-reason requests. These predate the refreshed packaging recipe and do not replace its current CI.
  • Fresh Linux CI overlay archive was SHA-256 verified. GPU1 passed all 14 addon tile/resize assertions and 13 SDK stop-reason compatibility requests. The runtime audit passed all 19 Linux modules. The bare-sidecar smoke chose CUDA; the host mapped libstdc++ during the load, so the static module audit supplies the runtime-independence check.
  • Current Fabric source was verified against the commit (normalizing archive line endings), rebuilt with ASan and UBSan, and passed all three focused mtmd tests with leak detection and halt-on-error enabled.

Known CI exception

The unchanged sharded embedding test fails at its original HF download URL (HTTP 401). A separate repair is in progress. This PR neither suppresses that test nor changes its assertions or CI labels; the exception is limited to this confirmed fixture failure.

Merge prerequisites

  1. Merge Fabric #457 and publish its updated vcpkg port.
  2. Replace this temporary overlay with the official dependency and pass current validation before merging this PR. Addon/runtime version and changelog updates belong in separate release PRs.

AI assistance: Codex assisted implementation and validation; manual review is required.

@DmitryMalishev DmitryMalishev added prebuilds CI: run only prebuild/cache stage (requires verified) run-cpp-addon-tests CI: run C++ addon tests (requires verified) run-desktop-addon-tests CI: run desktop integration tests (requires verified) labels Oct 30, 2026
@github-actions

github-actions Bot commented Oct 30, 2026 •

Copy link
Copy Markdown
Contributor

License compliance — clean

No new dependency license findings in this PR.

Warn-only (shadow) mode — this check does not block merges yet.

Updated automatically by the canonical license compliance workflow.

NOTICE presence (advisory)

Missing NOTICE (advisory, does not block):

  • ./docs/website
  • ./packages/asr-ggml/benchmarks/server
  • ./packages/fabric/test/integration
  • ./packages/llm-llamacpp/benchmarks/performance
  • ./packages/llm-llamacpp/benchmarks/server
  • ./packages/inference-addon-cpp/mobile
  • ./packages/sdk-e2e
  • ./packages/embed-llamacpp/benchmarks/performance
  • ./packages/embed-llamacpp/benchmarks/server
  • ./packages/vla-ggml/sim/server
  • ./.github/actions/release-merge-guard
  • ./.github/bare-toolchain

@DmitryMalishev
DmitryMalishev marked this pull request as ready for review October 30, 2026 16:14
@DmitryMalishev
DmitryMalishev requested review from a team as code owners October 30, 2026 16:14
@github-actions

Copy link
Copy Markdown
Contributor

Review Status

Current Status: ❌ PENDING
Approvals so far: none

Pending reviews: Needs 1 Management or Team Lead, and 1 more from Management, Team Lead, or Member.

Signed-off-by: Dmitry Malishev <dmitry.malishev@tether.io>
@github-actions

Copy link
Copy Markdown
Contributor

🧪 C++ Test Coverage Report

Coverage:

📊 Detailed Coverage
Filename                                         Regions    Missed Regions     Cover   Functions  Missed Functions  Executed       Lines      Missed Lines     Cover    Branches   Missed Branches     Cover
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
addon/FitVerdict.hpp                                  18                 0   100.00%           4                 0   100.00%          27                 0   100.00%          12                 0   100.00%
model-interface/NmtLazyInitializeBackend.cpp         100                17    83.00%          12                 1    91.67%         163                28    82.82%          67                20    70.15%
model-interface/NmtLazyInitializeBackend.hpp           2                 0   100.00%           1                 0   100.00%           1                 0   100.00%           0                 0         -
model-interface/TranslationModel.cpp                 351               154    56.13%          29                 7    75.86%         586               194    66.89%         227               121    46.70%
model-interface/TranslationModel.hpp                   4                 0   100.00%           4                 0   100.00%           6                 0   100.00%           0                 0         -
model-interface/nmt.cpp                               72                22    69.44%           9                 1    88.89%         139                28    79.86%          44                16    63.64%
model-interface/nmt.hpp                               51                 4    92.16%          11                 2    81.82%          53                 4    92.45%          28                 0   100.00%
model-interface/nmt_beam_search.cpp                  116                25    78.45%          10                 3    70.00%         254                32    87.40%          76                19    75.00%
model-interface/nmt_graph_decoder.cpp                164                78    52.44%          15                 7    53.33%         540               161    70.19%         112                69    38.39%
model-interface/nmt_graph_encoder.cpp                 54                13    75.93%           3                 0   100.00%         268                33    87.69%          37                16    56.76%
model-interface/nmt_loader.cpp                       334                74    77.84%          19                 0   100.00%         835               111    86.71%         205                74    63.90%
model-interface/nmt_state_backend.cpp                188                46    75.53%          20                 0   100.00%         426                79    81.46%         121                51    57.85%
model-interface/nmt_tokenization.cpp                  88                21    76.14%           8                 0   100.00%         135                36    73.33%          61                26    57.38%
model-interface/nmt_utils.cpp                        302                38    87.42%          26                 0   100.00%         429                40    90.68%         212                50    76.42%
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL                                               1844               492    73.32%         171                21    87.72%        3862               746    80.68%        1202               462    61.56%

@greptile-apps

greptile-apps Bot commented Nov 2, 2026 •

Copy link
Copy Markdown

RetriggerView in GreptileConfidence Score: 5/5

[Medium impact] No blocking code issue was found; keep the stated validation and official-dependency merge gates.

Summary

This PR connects the tiled-image geometry and resize fixes through a temporary Fabric overlay.

  • Qwen image requests use Fabric's corrected resize and tile geometry.
  • The translation fit test covers CPU-only and available-device results.

No actionable new issues were found. The previous and current heads have different merge bases with the supplied target, so this review covered the full PR diff.

Reviews (4) · Last reviewed commit: "fix: preserve current Fabric port runtim..." · Reviewed by Greptile

@github-actions

github-actions Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

🧪 C++ Test Coverage Report

Coverage:

📊 Detailed Coverage
Filename                                         Regions    Missed Regions     Cover   Functions  Missed Functions  Executed       Lines      Missed Lines     Cover    Branches   Missed Branches     Cover
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
addon/FitVerdict.hpp                                  18                 0   100.00%           4                 0   100.00%          27                 0   100.00%          12                 0   100.00%
model-interface/NmtLazyInitializeBackend.cpp         100                17    83.00%          12                 1    91.67%         163                28    82.82%          67                20    70.15%
model-interface/NmtLazyInitializeBackend.hpp           2                 0   100.00%           1                 0   100.00%           1                 0   100.00%           0                 0         -
model-interface/TranslationModel.cpp                 351               154    56.13%          29                 7    75.86%         586               194    66.89%         225               121    46.22%
model-interface/TranslationModel.hpp                   4                 0   100.00%           4                 0   100.00%           6                 0   100.00%           0                 0         -
model-interface/nmt.cpp                               72                22    69.44%           9                 1    88.89%         139                28    79.86%          44                16    63.64%
model-interface/nmt.hpp                               51                 4    92.16%          11                 2    81.82%          53                 4    92.45%          28                 0   100.00%
model-interface/nmt_beam_search.cpp                  116                25    78.45%          10                 3    70.00%         254                32    87.40%          76                19    75.00%
model-interface/nmt_graph_decoder.cpp                164                78    52.44%          15                 7    53.33%         540               161    70.19%         112                69    38.39%
model-interface/nmt_graph_encoder.cpp                 54                13    75.93%           3                 0   100.00%         268                33    87.69%          37                16    56.76%
model-interface/nmt_loader.cpp                       334                74    77.84%          19                 0   100.00%         835               111    86.71%         205                74    63.90%
model-interface/nmt_state_backend.cpp                188                46    75.53%          20                 0   100.00%         426                79    81.46%         121                51    57.85%
model-interface/nmt_tokenization.cpp                  88                21    76.14%           8                 0   100.00%         135                36    73.33%          59                25    57.63%
model-interface/nmt_utils.cpp                        302                38    87.42%          26                 0   100.00%         429                40    90.68%         212                50    76.42%
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL                                               1844               492    73.32%         171                21    87.72%        3862               746    80.68%        1198               461    61.52%

@github-actions

github-actions Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

🧪 C++ Test Coverage Report

Coverage:

📊 Detailed Coverage
Filename                                         Regions    Missed Regions     Cover   Functions  Missed Functions  Executed       Lines      Missed Lines     Cover    Branches   Missed Branches     Cover
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
addon/FitVerdict.hpp                                  18                 0   100.00%           4                 0   100.00%          27                 0   100.00%          12                 0   100.00%
model-interface/NmtLazyInitializeBackend.cpp         100                17    83.00%          12                 1    91.67%         163                28    82.82%          67                20    70.15%
model-interface/NmtLazyInitializeBackend.hpp           2                 0   100.00%           1                 0   100.00%           1                 0   100.00%           0                 0         -
model-interface/TranslationModel.cpp                 351               154    56.13%          29                 7    75.86%         586               194    66.89%         225               121    46.22%
model-interface/TranslationModel.hpp                   4                 0   100.00%           4                 0   100.00%           6                 0   100.00%           0                 0         -
model-interface/nmt.cpp                               72                22    69.44%           9                 1    88.89%         139                28    79.86%          44                16    63.64%
model-interface/nmt.hpp                               51                 4    92.16%          11                 2    81.82%          53                 4    92.45%          28                 0   100.00%
model-interface/nmt_beam_search.cpp                  116                25    78.45%          10                 3    70.00%         254                32    87.40%          76                19    75.00%
model-interface/nmt_graph_decoder.cpp                164                78    52.44%          15                 7    53.33%         540               161    70.19%         112                69    38.39%
model-interface/nmt_graph_encoder.cpp                 54                13    75.93%           3                 0   100.00%         268                33    87.69%          37                16    56.76%
model-interface/nmt_loader.cpp                       334                74    77.84%          19                 0   100.00%         835               111    86.71%         205                74    63.90%
model-interface/nmt_state_backend.cpp                188                46    75.53%          20                 0   100.00%         426                79    81.46%         121                51    57.85%
model-interface/nmt_tokenization.cpp                  88                21    76.14%           8                 0   100.00%         135                36    73.33%          59                25    57.63%
model-interface/nmt_utils.cpp                        302                38    87.42%          26                 0   100.00%         429                40    90.68%         212                50    76.42%
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL                                               1844               492    73.32%         171                21    87.72%        3862               746    80.68%        1198               461    61.52%

@github-actions

github-actions Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

🧪 C++ Test Coverage Report

Coverage:

📊 Detailed Coverage
Filename                                         Regions    Missed Regions     Cover   Functions  Missed Functions  Executed       Lines      Missed Lines     Cover    Branches   Missed Branches     Cover
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
addon/FitVerdict.hpp                                  18                 0   100.00%           4                 0   100.00%          27                 0   100.00%          12                 0   100.00%
model-interface/NmtLazyInitializeBackend.cpp         100                17    83.00%          12                 1    91.67%         163                28    82.82%          67                20    70.15%
model-interface/NmtLazyInitializeBackend.hpp           2                 0   100.00%           1                 0   100.00%           1                 0   100.00%           0                 0         -
model-interface/TranslationModel.cpp                 351               154    56.13%          29                 7    75.86%         586               194    66.89%         225               121    46.22%
model-interface/TranslationModel.hpp                   4                 0   100.00%           4                 0   100.00%           6                 0   100.00%           0                 0         -
model-interface/nmt.cpp                               72                22    69.44%           9                 1    88.89%         139                28    79.86%          44                16    63.64%
model-interface/nmt.hpp                               51                 4    92.16%          11                 2    81.82%          53                 4    92.45%          28                 0   100.00%
model-interface/nmt_beam_search.cpp                  116                25    78.45%          10                 3    70.00%         254                32    87.40%          76                19    75.00%
model-interface/nmt_graph_decoder.cpp                164                78    52.44%          15                 7    53.33%         540               161    70.19%         112                69    38.39%
model-interface/nmt_graph_encoder.cpp                 54                13    75.93%           3                 0   100.00%         268                33    87.69%          37                16    56.76%
model-interface/nmt_loader.cpp                       334                74    77.84%          19                 0   100.00%         835               111    86.71%         205                74    63.90%
model-interface/nmt_state_backend.cpp                188                46    75.53%          20                 0   100.00%         426                79    81.46%         121                51    57.85%
model-interface/nmt_tokenization.cpp                  88                21    76.14%           8                 0   100.00%         135                36    73.33%          59                25    57.63%
model-interface/nmt_utils.cpp                        302                38    87.42%          26                 0   100.00%         429                40    90.68%         212                50    76.42%
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL                                               1844               492    73.32%         171                21    87.72%        3862               746    80.68%        1198               461    61.52%

@github-actions

github-actions Bot commented Nov 3, 2026

Copy link
Copy Markdown
Contributor

🧪 C++ Test Coverage Report

Coverage:

📊 Detailed Coverage
Filename                                         Regions    Missed Regions     Cover   Functions  Missed Functions  Executed       Lines      Missed Lines     Cover    Branches   Missed Branches     Cover
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
addon/FitVerdict.hpp                                  18                 0   100.00%           4                 0   100.00%          27                 0   100.00%          12                 0   100.00%
model-interface/NmtLazyInitializeBackend.cpp         100                17    83.00%          12                 1    91.67%         163                28    82.82%          67                20    70.15%
model-interface/NmtLazyInitializeBackend.hpp           2                 0   100.00%           1                 0   100.00%           1                 0   100.00%           0                 0         -
model-interface/TranslationModel.cpp                 351               154    56.13%          29                 7    75.86%         586               194    66.89%         225               121    46.22%
model-interface/TranslationModel.hpp                   4                 0   100.00%           4                 0   100.00%           6                 0   100.00%           0                 0         -
model-interface/nmt.cpp                               72                22    69.44%           9                 1    88.89%         139                28    79.86%          44                16    63.64%
model-interface/nmt.hpp                               51                 4    92.16%          11                 2    81.82%          53                 4    92.45%          28                 0   100.00%
model-interface/nmt_beam_search.cpp                  116                25    78.45%          10                 3    70.00%         254                32    87.40%          76                19    75.00%
model-interface/nmt_graph_decoder.cpp                164                78    52.44%          15                 7    53.33%         540               161    70.19%         112                69    38.39%
model-interface/nmt_graph_encoder.cpp                 54                13    75.93%           3                 0   100.00%         268                33    87.69%          37                16    56.76%
model-interface/nmt_loader.cpp                       334                74    77.84%          19                 0   100.00%         835               111    86.71%         205                74    63.90%
model-interface/nmt_state_backend.cpp                188                46    75.53%          20                 0   100.00%         426                79    81.46%         121                51    57.85%
model-interface/nmt_tokenization.cpp                  88                21    76.14%           8                 0   100.00%         135                36    73.33%          59                25    57.63%
model-interface/nmt_utils.cpp                        302                38    87.42%          26                 0   100.00%         429                40    90.68%         212                50    76.42%
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL                                               1844               492    73.32%         171                21    87.72%        3862               746    80.68%        1198               461    61.52%

This branch was successfully deployed

1 active deployment
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

prebuilds CI: run only prebuild/cache stage (requires verified) run-cpp-addon-tests CI: run C++ addon tests (requires verified) run-desktop-addon-tests CI: run desktop integration tests (requires verified)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant