Merge pull request #196 from mudler/row/ENG-RELEASE-BINARIES

release: ship complete W1-W13 binary matrix

Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: Codex:GPT-5 [Codex]

Author: localai-bot

.agents/NOW.md

@@ -29,7 +29,7 @@ Work: exact-chunks on main `1ce0d662b`; sm_120 measured at `3d2581551`.
 | Vulkan 27B | decode **MET 4.36 vs 4.35** (barriers OFF). **LOADMEM: load held the model TWICE, VmRSS 100.759 -> 53.413 GiB** | Load-phase host build is the new peak |
 | `BACKEND-ROCM` | **(b) fix in; #140 gfx1201 hipBLAS + Gemma-4 MoE landed (contributor, authorship-preserved); W0 green 4 archs** | compile + M2 ([spec](specs/rocm-unified-memory-b.md)) |
 | TP spike #287 (PR #143) | **TP-W1 LANDED**: rank-group table + TP handle (6/6); DSR leak FIXED (unblocks #127/#154/#155) | TP-W2 (linears + loader) |
-| Release | **ACTIVE; W5 19/19+10/10; contract 30/30** | #141; artifacts pending |
+| Release | **ACTIVE; required W1-W11/W13 implemented in #196** | Finish hosted ten-SM proof; rebase/push; run full eight-tuple dry run |
 | Surface coverage (`ARCH-ONE-SURFACE`) | ROW 8 + #139; **embeddings live (#137): model, runner, ABI v15, endpoint, fold 4/4-231** | Real-checkpoint oracle cosine |
 
 In-flight, default-OFF, not pushed: see the row's spec.

.agents/completed/state-events/2026-08/STATE-20260809T150001-001.md

@@ -0,0 +1,30 @@
+# W6 server package claimed after empty release diagnosis
+<!-- state-event: STATE-20260809T150001-001 -->
+
+## Context
+
+The `v0.0.2-alpha1-ci-test` release proved the expected W5 boundary: GitHub
+created the release with zero assets and launched zero release-event workflows.
+PR #141 explicitly excluded W1-W4 and W6-W13; it merged only the manifest
+schema and tooling at `bd20da30`.
+
+## Outcome
+
+`CLAIM-ENG-RELEASE-BINARIES-W6` owns the first missing executable boundary:
+canonical `vllm-server`, a server-only install component, deterministic
+staging/archive targets, and an empty-prefix to archive to empty-extraction to
+`bin/vllm-server --help` gate. The existing library/header install surface must
+remain unchanged. W1-W4, W7-W13, publication, GPU execution, runtime-model
+correctness/performance, downloads, services, and channel advancement remain
+pending at this checkpoint.
+
+## Evidence
+
+The claim is PR #196 on branch `row/ENG-RELEASE-BINARIES`, rebased onto
+`origin/main` `26a128c2`. The accepted dependency order and release contract are
+in `.agents/specs/release-binary-matrix.md`.
+
+## Next action
+
+Implement the focused W6 test and prove it fails because the current target is
+named `server` and no server install/archive rule exists.

.agents/completed/state-events/2026-08/STATE-20260809T160000-001.md

@@ -0,0 +1,33 @@
+# W6 installed server package green
+<!-- state-event: STATE-20260809T160000-001 -->
+
+## Context
+
+PR #196 implements W6 on rebased claim base `26a128c2`. The server remains a
+thin public C-ABI client while linking the static core, installs as
+`bin/vllm-server` through component `vllm-server`, and exposes deterministic
+`vllm-server-stage` and `vllm-server-archive` targets. Packaging installs into
+a new empty prefix and normalizes archive ordering, owner, modes, and timestamps.
+
+## Outcome
+
+The row remains `ACTIVE`. W1-W4 and W7-W13 remain pending. This development
+archive has no W7 allowlist/dependency/RPATH audit, VERSION, manifest, SBOM,
+licenses, provenance, or final checksum and has not been published. No model
+runtime, correctness, performance, or channel claim advances.
+
+## Evidence
+
+RED: `python3 tests/scripts/test_server_package.py` failed because target
+`vllm-server-archive` did not exist. GREEN: the clean CPU test completed 1/1 in
+105.000 seconds; a second run against the prebuilt tree completed in 3.285
+seconds. It reproduced the archive SHA256, extracted into a second empty tree,
+ran canonical `bin/vllm-server --help` with loader-path overrides removed,
+proved Linux `ldd` has no `libvllm`, and confirmed the existing `vllm.h`, static,
+and shared library installs remain present. GitHub Actions repeated the package
+gate successfully at the pre-rebase immutable head.
+
+## Next action
+
+Continue PR #196 with W1-W4 and W7-W13, beginning with the cross-family CUDA
+fat-build red gate from the accepted dependency graph.

.agents/coordination.md

@@ -134,19 +134,22 @@ ships DEFAULT-OFF pending an operator re-measurement. dgx build/gate roots
 `dgx.casa:~/vkbase` (main control) and `~/vkbar` (this branch), both
 `-DVLLM_CPP_VULKAN=ON`, every GPU stage under `flock $HOME/gpu.lock`.
 
-**Server binary release manifest W5 (`ENG-RELEASE-BINARIES`, 2026-08-08,
-`CLAIM-ENG-RELEASE-BINARIES-W5`).** Codex (GPT-5), isolated worktree
+**Server binary release W1-W13 (`ENG-RELEASE-BINARIES`, 2026-08-09,
+`CLAIM-ENG-RELEASE-BINARIES-W1-W13`).** Codex (GPT-5), isolated worktree
 `/home/mudler/_git/vllm.cpp-release-binaries`, branch
-`row/ENG-RELEASE-BINARIES`, base `origin/main` `b38f78a7`. PR #129 merged the
-accepted release matrix; the current claim is W5 only: a versioned manifest
-schema, deterministic generator/validator, canonical fixtures, mutation tests,
-and the narrow release-contract/record surfaces those tests require. No W1-W4
-CUDA/CPU implementation, W6 archive/install target, release workflow,
-published artifact, download, GPU, model, kernel, or service change is in
-scope. Draft PR #141 is the claim. W5 is implemented and green at 19/19 after
-the fresh review's ten production-removal mutations were killed; the row is
-`ACTIVE`, while every archive, staged smoke, runtime, correctness, performance,
-install/package and publication claim remains pending.
+`row/ENG-RELEASE-BINARIES`, base `origin/main` `81291a89`. W5 merged in PR #141
+at `bd20da30`; developer direction binds every remaining W1-W13 checkpoint to
+the single draft PR #196. W6's clean CPU gate is GREEN: the canonical
+static-core binary installs through component `vllm-server`; two package runs
+produce identical archive bytes; an empty extraction runs `--help` without a
+dynamic `libvllm`; and the existing library/header install remains present.
+Required W1-W11/W13 implementation is now complete in the same draft PR:
+ten-SM gencode/AOT, adaptive CPU tiers, extracted-archive and supply-chain gates,
+least-privilege immutable handoff, eight primary bundles, generated indexes,
+attestation, and exact-file publication. Local CPU/Vulkan/mutation gates are
+green. The row remains `ACTIVE`; hosted ten-SM completion, the full eight-tuple
+dry run, matching-hardware evidence, merge, and tagged publication remain
+pending. W12 stays optional/non-primary.
 
 **CPU grouped keep-quant GEMM activation-dtype P0 (`QUANT-GGUF-CIQ-GEMM`,
 2026-08-06, `CLAIM-QUANT-GGUF-CIQ-GROUPED-DTYPE`).** Claude Code
@@ -1425,6 +1428,7 @@ table, tests, CMake. Details in the state-log entry of the same date.
 
 | Claim | Row IDs | Agent | Worktree / remote dir | Branch | Owned scope | State | Last update |
 |---|---|---|---|---|---|---|---|
+| `CLAIM-ENG-RELEASE-BINARIES-W1-W13` | `ENG-RELEASE-BINARIES` (`ACTIVE`; complete release matrix) | Codex (GPT-5) | `/home/mudler/_git/vllm.cpp-release-binaries`; inline execution in the existing isolated worktree | `row/ENG-RELEASE-BINARIES`, base `origin/main` `81291a89`, draft PR #196 | Complete W1-W13 contract in one PR: fat-CUDA gencode and AOT, adaptive CPU tiers, staged validation and supply chain, least-privilege release automation, all declared bundles, generated index, and tagged-release audit. W5 is inherited from main; ROCm remains blocked by contract | `ACTIVE` | 2026-08-09 — required W1-W11/W13 implementation complete; local CPU/Vulkan/mutation gates green; hosted ten-SM completion, full eight-tuple dry run, matching-hardware gates, rebase/merge, and tagged publication pending; W12 optional/non-primary |
 | `CLAIM-ENG-RELEASE-BINARIES-W5` | `ENG-RELEASE-BINARIES` (`ACTIVE`; W5 only) | Codex (GPT-5) | `/home/mudler/_git/vllm.cpp-release-binaries`; CPU/build-time metadata tooling only, no GPU/download/service work | `row/ENG-RELEASE-BINARIES`, base `b38f78a7`, claim commit `29107d0b`, draft PR #141 | W5 implemented: versioned manifest schema + deterministic generator/validator, canonical synthetic CPU/CUDA fixtures, fail-closed mutation tests, release checker/registration and required record/doc checkpoints. Excludes W1-W4, W6-W13, archives, install/package/publish workflows and runtime artifacts | `ACTIVE` | 2026-08-08 — W5 19/19; fresh-review production removals 10/10 killed; accepted release suite 30/30; no archive or real runtime/correctness/performance evidence |
 | `CLAIM-KIMI-LINEAR-W0` | `MODEL-TEXT-kimi-linear-kimi-linear-for-causal-lm` (stays SPIKE — dedicated W0 spike) | Claude Code (opus-4-8) | isolated worktree `.claude/worktrees/agent-a771cc029e6843be0`; CPU-only, records-only — NO build, NO GPU, NO download (two GPU jobs queued ahead; the W0 GPU golden capture is a SEPARATE later step) | branch `worktree-agent-a771cc029e6843be0`, base `origin/main` HEAD `10dd23ee` | The FULL dedicated W0 spike for `KimiLinearForCausalLM` (Kimi-Linear-48B-A3B) per the spike-first protocol, so W1 implementation can start immediately. Owns ONLY: NEW `.agents/specs/kimi-linear.md`, the `MODEL-TEXT-kimi-linear-*` matrix row (Spike link → the dedicated spec + note; STAYS `SPIKE` because it is actively claimed — protocol forbids a claimed row from being `READY`; checklist mark stays `📋`), this claim row + the narrative block below, the roadmap breadth note, `docs/STATUS.md`/`docs/BENCHMARKS.md`/`docs/FEATURES.md` one-liners, the `.agents/NOW.md` live-claim row + stamp, and one `.agents/state.md` entry. **NON-COLLISION:** records-only — touches NO model/kernel/registry/loader source, NO CMake, NO test. Co-owns the Kimi-Linear row with `CLAIM-MLA-DEEPSEEK` (MLA half) + `CLAIM-KDA-KERNEL` (KDA host refs), exactly as the K3 row is co-owned by `CLAIM-KIMI-K3-SCOPE`/`CLAIM-KIMI-K3-W2-W5`. | `DONE` | 2026-08-05 — **W0 DEDICATED SPIKE LANDED (records-only, NOT pushed).** Authoritative `config.json` fetched (27 layers = 20 KDA + 7 NoPE-MLA; 256e/top-8/1-shared sigmoid `noaux_tc` `routed_scaling=2.446` `first_k_dense_replace=1`; `num_nextn_predict_layers=0` ⇒ no MTP); reuse-vs-new map with our `file:line`; HW-fit (FITS one GB10, 91.5 GiB / 0.77× pool — real e2e SACRED gate reachable); W0-W7 breakdown + GPU golden-capture recipe. NET-NEW = KDA device kernel (host refs landed, `CLAIM-KDA-KERNEL`), NoPE-MLA branch, hybrid schedule/het-KV, loader name-map. Record checkers green (`check-model-checklist`, `check-agent-record`, `check-doc-checkpoint`, `check-now-current`). |
 | `CLAIM-KIMI-LINEAR-W1` | `MODEL-TEXT-kimi-linear-kimi-linear-for-causal-lm` (stays SPIKE — W1 registry/config/loader scaffolding; forward REFUSES-by-name) | Claude Code (opus-4-8) | isolated worktree `.claude/worktrees/agent-a11ae231a71e8694b`; CPU-only `build-cpu` (`-DVLLM_CPP_CUDA=OFF` Release); NO GPU, NO download — additive TU + one REGISTER line, forward is a `VT_CHECK(false)` stub | branch `worktree-agent-a11ae231a71e8694b`, base `origin/main` HEAD `053116df` | Kimi-Linear-48B-A3B W1 — registry + config + loader + KV-spec scaffolding so the W3-W6 forward can start. Owns ONLY: NEW `include/vllm/model_executor/models/kimi_linear.h`, NEW `src/vllm/model_executor/models/{kimi_linear_registry,kimi_linear_weights,kimi_linear}.cpp`, NEW `tests/vllm/models/test_kimi_linear_scaffold.cpp`, its two CMake registration lines (`CMakeLists.txt` source list + `tests/CMakeLists.txt`), the `KimiLinearForCausalLM` sorted-set + error-message + model-property inserts in `tests/vllm/models/test_model_registry.cpp`, the `MODEL-TEXT-kimi-linear-*` row cells + checklist Status (STAYS `SPIKE`/`📋` — the forward refuses, rollup UNCHANGED), this claim, `.agents/NOW.md`, `docs/STATUS.md`/`docs/BENCHMARKS.md`/`docs/FEATURES.md` one-liners, and one `.agents/state.md` entry. **NON-COLLISION:** additive TU + one REGISTER line ⇒ ZERO edit to any shared array; the forward is a `VT_CHECK(false)` refuse stub so NO production/device path changes; co-owns the Kimi-Linear row with `CLAIM-MLA-DEEPSEEK` + `CLAIM-KDA-KERNEL` + `CLAIM-KIMI-LINEAR-W0`; MUST NOT touch README, Metal/SACRED/apex/darwin, or any other model/kernel source. | `DONE` | 2026-08-05 — **W1 CPU SCAFFOLDING LANDED (foreground, NOT pushed).** Additive registry (`kimi_linear`/`KimiLinearForCausalLM`, `is_hybrid`, `supports_multimodal=false`) + `ParseKimiLinearParams` (20 KDA + 7 NoPE-MLA schedule, MLA 512/128/64/128 q_lora-null, 256e/top-8/1-shared sigmoid `noaux_tc` 2.446, `first_k_dense_replace=1`; asserts `mla_use_nope`/`q_lora==null`) + `EnumerateKimiLinearTensors` name-map VERIFIED vs the real HF safetensors index (MoE = `block_sparse_moe.*`, the correction of the DERIVED K3 `mlp.*`) + loader THROWS BY NAME on missing/mis-shaped tensors + het KV spec (MLA latent-576 + KDA mamba `12288×3`/`32×128×128`) + REFUSE-by-name forward. `test_kimi_linear_scaffold` **9/9·83** + `test_model_registry` **24/24** + `test_kimi_k3_scaffold` 6/6 unchanged; clean CPU Release build; `check-fusion-consistency`/`check-runner-routing-consistency` green (refuse stub skipped); record checkers rc=0. RESIDUAL (W3-W6): KDA device kernel + NoPE-MLA route + sigmoid-noaux MoE + het-KV born-on-runner forward + the e2e SACRED gate (spec §8 recipe). |