release: add versioned binary manifest (W5) - #141
Merged
Conversation
mudler
added a commit
that referenced
this pull request
Aug 8, 2026
Implement W5 with a deterministic stdlib-only manifest generator, versioned schema, canonical CPU/CUDA fixtures, and fail-closed mutation coverage. Advance only the release program lifecycle to ACTIVE while preserving every artifact and runtime gate as pending. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Codex:GPT-5 [Codex]
Collaborator
Author
|
CI record-gate repair at
No release artifact/runtime/performance claim changed; reviewed W5 implementation blobs remain untouched. |
mudler
added a commit
that referenced
this pull request
Aug 8, 2026
The at-a-glance row, the section heading and the closed-row table all called the benchmarked model Laguna-XS-2.1. The measured checkpoint is poolside/Laguna-S-2.1-NVFP4: 118B total / ~8B active MoE, 48 layers, 256 experts, ~67 GiB. The label came from the local checkpoint directory being named laguna-xs-nvfp4. Evidence that the two names are one benchmark: the same 37.55 -> 44.46 vs vLLM 43.10 pair appears in this file under "Laguna-XS NVFP4" and in the same document's row for "Laguna-S-2.1 MoE (LagunaForCausalLM, 118B/8B)", both dated 2026-08-04; and the NVFP4 arm spec pins the checkpoint at poolside/Laguna-S-2.1-NVFP4, ~67 GiB, with layers 1..47 MoE. The section now states the model geometry and says where the XS label came from, so it cannot drift back. The reproduce row keeps the real directory name with a note that it holds the S-2.1 checkpoint. Numbers, ratios and evidence anchors are unchanged; this is a naming correction only. FEATURES.md and README are untouched: they list "Laguna-S / Laguna-XS 2.1" as a model family, which is a separate question from which checkpoint was measured. No open issue or PR covers this (searched issues and PRs for laguna naming; open PRs are #127, #128, #140, #141, none related). FOLLOWING_AGENTS_PROTOCOL Assisted-by: Claude Code:claude-opus-5 [ClaudeCode]
mudler
added a commit
that referenced
this pull request
Aug 8, 2026
Ground the two direct GeGLU call sites and the runner device-identity leak, bind red-first tests, two independent repair commits, mutation review, and the #141 reconciliation sequence. FOLLOWING_AGENTS_PROTOCOL Assisted-by: Codex:GPT-5 [Codex]
mudler
added a commit
that referenced
this pull request
Aug 8, 2026
Ground the two direct GeGLU call sites and the runner device-identity leak, bind red-first tests, two independent repair commits, mutation review, and the #141 reconciliation sequence. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
mudler
added a commit
that referenced
this pull request
Aug 8, 2026
Ground the two direct GeGLU call sites and the runner device-identity leak, bind red-first tests, two independent repair commits, mutation review, and the #141 reconciliation sequence. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
mudler
force-pushed
the
row/ENG-RELEASE-BINARIES
branch
4 times, most recently
from
August 9, 2026 01:39
86b04c2 to
d042533
Compare
localai-bot
marked this pull request as ready for review
August 9, 2026 02:19
mudler
force-pushed
the
row/ENG-RELEASE-BINARIES
branch
from
August 9, 2026 07:36
d042533 to
82af0d2
Compare
mudler
approved these changes
Aug 9, 2026
Rebuild the reviewed W5 schema, deterministic generator/validator, canonical CPU/CUDA fixtures, fail-closed tests, and pending-only lifecycle records as one post-cutover change on current main. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
Preserve rolled Gemma4 evidence, attach the Vulkan state anchor to its heading, compact the live digest below budget, restore public keyed-document ratchets, and classify the new server and ROCm/Gemma environment variables without weakening any checker. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
Classify the versioned release manifest schema explicitly, keep unknown release paths fail-closed, and cover the two existing top-level documentation surfaces so the tracked-tree invariant remains complete. RED: release/manifest-v1.schema.json raised ValueError as unclassified. GREEN: test_check_pr_size 21/21. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
Classify the release binary contract validator as product code rather than a governance-policy checker, while preserving the fail-closed governance classification for every generic check-* entrypoint. RED: the explicit product-class assertion observed governance_checker. GREEN: test_check_pr_size 21/21. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
Classify release-manifest JSON fixtures as assets, bind the historical agent-record mutation suite, and keep the two W5 product scripts at the exact 900-line review budget without a waiver. Record the green size gate in the keyed public rows. RED: the actual PR-size gate rejected missing checker evidence and 2222 product lines. GREEN: focused release/size suites and staged preflight pass; governed product total is 900. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
RED: the release PR exceeded its product budget by the allowlist's ten configuration lines. GREEN: the exact-path class and mutation test restore the intended 900-line product total. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
Compact the OpenAI capability cell into its binding result, lower the shrink-only character ratchet, and record the gate beside the W5 benchmark evidence. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-5 [Codex]
mudler
force-pushed
the
row/ENG-RELEASE-BINARIES
branch
from
August 9, 2026 08:46
82af0d2 to
4b635fb
Compare
13 tasks
rohitpaul
pushed a commit
to rohitpaul/vllm.cpp
that referenced
this pull request
Aug 9, 2026
User-directed: alongside the downloadable archives in ENG-RELEASE-BINARIES (mudler#117, PR mudler#141), publish container images to GHCR from GitHub Actions. Issue mudler#170 carries the public description. The image is not a second packaging format. It ships exactly the staged tree the release-binary matrix already defines - bin/vllm-server, VERSION, manifest, SHA256, SBOM, provenance, licenses - with ENTRYPOINT vllm-server and nothing else in it. If the two lanes grow separate layouts that is a bug, so the row records the dependency explicitly: the staging tree and install rule are owed by ENG-RELEASE-BINARIES and do not exist yet. One package, lane in the tag: ghcr.io/mudler/vllm.cpp:<version>-cuda / -vulkan / -cpu, moving :latest-cuda / :latest-vulkan / :latest-cpu, bare :latest aliasing cpu. Version tags immutable. rocm is recorded blocked-preview tracking its binary channel (mudler#41, mudler#132). Every lane is a linux/amd64 + linux/arm64 multi-arch manifest built on native runners rather than QEMU. arm64 is not a courtesy here: the gate hardware this project is measured on is aarch64 throughout - GB10 sm_121a, Thor sm_110 (mudler#168), Orin sm_87 - and an emulated CUDA build does not finish inside a runner's lifetime. Metal and MLX are recorded NOT-CONTAINERIZABLE, not deferred. There is no macOS container runtime and no Metal passthrough into a Linux VM, so those lanes can only ever be static binaries. Writing it as a boundary keeps it from being re-opened as pending work later. The accepted release-binary contract block is deliberately untouched: this is a separate distribution channel with its own artifact format, registry, tag contract and publish flow, so it gets its own row and its own future spike rather than widening a design that has already been reviewed and is guarded by a 30-test mutation suite. Entered at INVENTORIED with planned: specs/container-images.md. Under POL-SPIKE-FIRST the row cannot advance until that spike exists; no image, workflow or registry package is claimed by the ENGINE_ROWS 143 -> 144 bump. docs/STATUS.md and docs/BENCHMARKS.md carry the line the doc-checkpoint gate requires. The STATUS line is paid for out of the page, as its ratchet demands: the Tier-A1 fold paragraph was a run-by-run log of a 2026-07-30 branch, down to a literal "commit <this>, NOT pushed", on a page whose contract is one binding current-state line per capability. It collapses to its binding result plus pointers, and the run detail was already in .agents/benchmark-record.md, .agents/state.md and the fold-plan spec. The unflattering parts stay on the page on purpose - only OLMo-2 has a committed golden, Granite and StableLM skip rather than gate, dflash and deepseek_v2 are build-verified only. Ratchet lowered 279130 -> 276960. Gates: check-agent-record (ENGINE=144), test_agent_record 13/13, test_doc_checkpoint 40/40, check-release-binary-contract, check-readme-structure, check-public-doc-tables, check-policy, check-protocol-consistency, check-commit-trailers, check-doc-checkpoint - all OK on a worktree pinned at 994cd8d. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Claude-Code:claude-opus-5 [Claude Code]
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
2 participants
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.
Claim
Implements W5 of ENG-RELEASE-BINARIES from the accepted release matrix in #129. This PR is the active CLAIM-ENG-RELEASE-BINARIES-W5 claim.
Scope
Excluded from this W5 PR: W1-W4 and W6-W13, install/package/archive/publish targets, runtime artifacts, GPU execution, downloads, services, and release channel advancement.
Evidence
No archive, runtime, correctness, performance, download, or publication evidence is claimed by W5.