pin v2 payload: engine 2611021012001, cuda 2610311711001, cuda12 2610311711002, sbsa 2610311711003, vulkan 2611011644001, macos 2610311711005, media 2611012031001

.gitattributes

@@ -355,3 +355,5 @@ components/media/2611012031001/oc-espeak-linux-x86_64.so filter=lfs diff=lfs mer
 components/media/2611012031001/oc-espeak-linux-aarch64.so filter=lfs diff=lfs merge=lfs -text
 components/media/2611012031001/oc-espeak-win-x86_64.dll filter=lfs diff=lfs merge=lfs -text
 components/media/2611012031001/oc-espeak-macos-aarch64.dylib filter=lfs diff=lfs merge=lfs -text
+components/engine/2611021012001/opencoti-0.10.5-c14-2611021012001 filter=lfs diff=lfs merge=lfs -text
+components/engine/2611021012001/opencoti-0.10.5-c14-2611021012001.exe filter=lfs diff=lfs merge=lfs -text

components/cuda/2610311711001/BUILD_INFO.cuda.md

@@ -2,7 +2,7 @@
 
 Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
 
-Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2610312243001, 2611010802001, 2611011335001, 2611011619001, 2611012008001, 2611012031001.
+Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2610312243001, 2611010802001, 2611011335001, 2611011619001, 2611012008001, 2611021022001, 2611021012001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|

components/cuda12/2610311711002/BUILD_INFO.cuda12.md

@@ -2,7 +2,7 @@
 
 Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
 
-Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2611010802001, 2611011335001, 2611011619001, 2611012008001, 2611012031001.
+Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2611010802001, 2611011335001, 2611011619001, 2611012008001, 2611021022001, 2611021012001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|

components/engine/2611021012001/BUILD_INFO.engine.md

@@ -0,0 +1,53 @@
+# engine 2611021012001
+
+Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
+
+| file | platform | kind | sha256 | bytes |
+|---|---|---|---|---|
+| `opencoti-0.10.5-c14-2611021012001` | any | bin | `e76099ee3756332e20c5681798a3620ce983d429cc30882f02e9350de4e50590` | 146965142 |
+| `opencoti-0.10.5-c14-2611021012001.exe` | win-x86_64 | bin | `e76099ee3756332e20c5681798a3620ce983d429cc30882f02e9350de4e50590` | 146965142 |
+
+ABI `ggml` = `bac5050ddc8c58c51f0b059a7f9753b33af0ed79d355090e7c9a17ffaaaf340a` (exported) — sha256 of this list:
+
+```
+llama.cpp/ggml/include/ggml-alloc.h 94e4cd069b9313b2ceb35dacec901981e0bb478d8bb31035b7126be091998c23
+llama.cpp/ggml/include/ggml-backend.h 764d1640ad62579513c4837539708f89e8603c9dbeae053a13d1cbd84a82c865
+llama.cpp/ggml/include/ggml-cuda.h 674ea064021cf5b9970e78f1209e513dd23350b94a44a705a27eec1423fe4b0a
+llama.cpp/ggml/include/ggml-metal.h 322f36cd30f3e9e7aad7b5b9bc63078012fd0b7706ac4e24f5721b604f3d8980
+llama.cpp/ggml/include/ggml-neo-pipeline.h 190f39e183542d16588a3104d8cb4359bf52fc7a62afe8d8cc4c822f4085086d
+llama.cpp/ggml/include/ggml-oc-kvarn-range.h 76635fdd8978632f670640ddf5125a666441e3d47c680bb8b5c0a099e4861202
+llama.cpp/ggml/include/ggml-oc-ledger.h c1be11d69a57a1e721f1ae8720b87887d239ac0183d4277fbaa07f1be257d20c
+llama.cpp/ggml/include/ggml-vulkan.h f9df4f7161a84ce7600d53c3fac8a62837d5716676c9f38cd340699ef1c070d9
+llama.cpp/ggml/include/ggml.h ecfbf114f9e9151d22e30ef6d5139570c5c41b595843ca4f99125bd0196709aa
+llama.cpp/ggml/include/opencoti-devtype.h 94dea946173449bb76bffd7f733ab822fe658fe7198992de750ac012d29308ec
+llama.cpp/ggml/src/ggml-backend-impl.h f9fdfe6bae61d1387593b40fc0f90ceee490c6a339ec6d7388c51e4fca318d8f
+llamafile/gpu_backend.h 4929c36c034b6589e88653bcb7a5c5a225743a07320f64c0857d92bdaf048208
+```
+
+ABI `media` = `b099409b3029a6e380268e31d1caefa6706569961d32e72b3543fbc73903d95c` (exported) — sha256 of this list:
+
+```
+llamafile/oc-audiocpp/audiocpp.h 6ad0b55d5f28adc9ad60a45bf9a7caa428c4f5441389a6932d6670a8e2a90d73
+llamafile/oc-codec/oc_codec_sidecar.h f2c9001d1414aa2a55533b867b79c52a52c682558e0234c5bebd30bf97b91005
+```
+
+ABI `loader` = `d6ff34022f1d3fb5af56ca0c80e3f4e552bf09f1bebdf0cb5f314a454bf38dbc` (exported) — sha256 of this list:
+
+```
+.cosmocc/4.0.2/bin/ape-m1.c 78af79e20abbb3f99a97355959b59bd58949564064adb754f0302ebabb4bf7a3
+```
+
+**c14 dev snapshot — the development build of the c14 release, for integration testing.** Engine 2611021012001 (`opencoti-0.10.5-c14`, dev channel) is built from the same source as the c14 release engine 2611021022001 (the 12338 source files the two trees share are identical by sha256 (0 differ; clean-room /mnt/sdc/opencoti-cleanroom-c14r6 at e34d4551d5)). The libraries are the c14 release index's. This engine ran the glibc 2.28 route gate (Vulkan + CUDA) on bs2 with the release libraries (cuda, cuda12, vulkan); the release gates ran on 2611021022001 (see the release notes).
+
+**c14 r6 (2026-11-02) — a re-cut of c14.** Same tag, new engine 2611021022001 (r5: 2611012008001; bare `ff11a01625c4`, r5 `c93020caeb14`): `release/c14-r6` = the c14 r5 source + `0831-c14-router-gpu-forward` (c14 57.16 / op-323, bug-4327; xollama #26 joeblowma; owner 2026-11-02 10:01 "fix it for c14 r6 and answer joeblowma"). Router mode (`--server --models-preset x.ini` / `--models-dir`) hands its `--gpu` to every model instance it spawns; a preset row `gpu = …` (per model or `[*]`) names the backend per model and wins over the router's; `LLAMA_ARG_GPU` is the flag's env twin. Until r5 every child booted `auto` — Metal, CUDA, AMD, Vulkan in that order — whatever the router was started with (`--gpu` is the launcher's flag, stripped before the server parses argv and never rendered into a child's argv), and the ini refused the key: a router started with `--gpu vulkan` on a box with an NVIDIA driver served every model on CUDA. Gate: `scripts/router-gpu-gate.sh` on bs2 GPU1 — the r5 bare reproduces (child `cuda: loaded`), the r6 engine's children load Vulkan through the flag, the ini row and the env, and a per-model `gpu = nvidia` wins. The capability table is unchanged (79 rows).
+
+**c14 r5 (2026-11-01) — a re-cut of c14.** Same tag, new engine 2611012008001 (r4: 2611011619001; bare `c93020caeb14`, r4 `0f22e977cd6c`): `release/c14-r5` = the c14 r4 source + three patches. `0828-c14-media-flags-table` (c14 57.14 / op-321, after bug-4319): the launcher's "valid without -m" check and the server's media-engine detection expand ONE table (`common/oc-media-flags.h`), the hand-kept lists are gone; the same six flags waive `-m`. `0829-c14-features-table` (c14 57.7 / op-312, bug-4320; xollama #2041/#2042): `/props` `features`, `--server --print-features` (model-free) and this pin's feature rows come from ONE table (`common/oc-features.h`); the pin is derived from the engine at the cut and refused on any difference; the four rows the c14 pin declared without the engine reporting them (`arch_lfm3_v1`, `vulkan_matvec_tune_v1`, `auto_mtp_adaptive_v1`, `moe_strategy_v1`) are reported now, and a loaded sound-effects engine reports `audio_sfx_audiocpp_v1`. `0830-c14-polykv-idle-skip` (c14 57.8 / op-313; xollama #2045/#2092): the default idle-slot save/clear skips pool-attached slots — measured, the pool prefix was never evicted (an 8870-token root re-attached with 18 prompt tokens, flag or no flag) but the default attempted a save of every idle slot at every task launch, the unrelated request that triggers the save of an idle pool-serving slot pays for it (891 vs 160 ms at 8.9k tokens kvarn3 on a 1.5B); feature row `idle_slot_pool_safe_v1`: a client drops `--no-cache-idle-slots` on it; with the flag the engine behaves byte for byte as r4. Feature rows: r4's 78 + `idle_slot_pool_safe_v1` = 79.
+
+**c14 r4 (2026-11-01) — a re-cut of c14.** Same tag, new engine 2611011619001 (r3: 2611011335001, r2: 2611010802001, r1: 2610312243001; bare `0f22e977cd6c`, r3 `2261d16fef14`): `release/c14-r4` = the c14 r3 source + `0826-c14-sfx-media-only` (bug-4319, roadmap 57.13 / op-320, xollama #2072) + `0827-c14-vk-mmv-one-col-scalar-acc` (roadmap 57.12 / op-319; shaders only — it changes the Vulkan libraries, not the engine's behaviour): `--sfx-model` joins the launcher's media-only list in `llamafile/main.cpp`, so a `--server --sfx-model X` without `-m` boots (on r3 it exited "missing required -m MODEL.gguf"). One line in the launcher; both Vulkan libraries rebuilt (0827), every other library r3's bytes; the feature rows are r3's 78. Gated: the sound-effects gate with the two media-only arms (bs2 GPU1, r3 = the failing control), 40 control / glibc / bonsai ident, 42 / 43 / 44, 55 (12a-g).
+
+**c14 r3 (2026-11-01) — a re-cut of c14.** Same tag, new engine 2611011335001 (r2: 2611010802001, r1: 2610312243001; bare `2261d16fef14`, r2 `9f4bfaf682a2`): `release/c14-r3` = the c14 r2 source + `0824-c14-sfx-route` (roadmap 57.10 / op-317: `--sfx-model`, `POST /v1/audio/generations` mp3 | wav | pcm | json through the `oc-audiocpp` sidecar's `stable_audio` family, feature `audio_generations_v1`, `/props media.sfx`, one clip at a time with 503 + Retry-After, 501 without a model; bug-4316: the sidecar thread's CPU mask widened around load and run — a 2 s clip 170 s → 4–5 s on bs2, speech gains the same) + `0825-c14-vk-mmv-one-col` (roadmap 57.11 / op-318, bug-4315: the host side of the one-column integer-dot mat-vec pipelines — the engine's part is the pipeline selection in `ggml-vulkan.cpp`, shipped inside the Vulkan libraries; the bare carries no Vulkan code). Chain `0001`–`0825`. Built in the clean-room from `release/c14-r3` (85dab0deae) with the id minted before the build (the first clean-room run of the day went without it and said `build unknown` — bug-4318; the lane now refuses). Feature rows: r2's 77 plus `audio_generations_v1` (78). Owner 2026-11-01 12:55: "cut now the c14 re-release with it, publish on hf dev and hf pub". Gates: the scoped re-cut set + the two reproducers (the sound-effects route gate on bs2 GPU1; the Windows gate's `vulkan2-igpu` arm on eleven2go against the c13 r6 library).
+
+**c14 r2 (2026-11-01) — a re-cut of c14.** Same tag, new engine 2611010802001 (r1: 2610312243001; bare `9f4bfaf682a2`, r1 `72d949a3cbdd`): `release/c14-r2` = the c14 tag + `0823-c14-cu12-win-published-name` (bug-4313) — on Windows the CUDA 12 legacy library is now found beside the engine under its published name `ggml-cuda-cu12-win-x86_64.dll` (r1 searched `ggml-cuda-cu12.dll` and the Linux spelling only, so a consumer staging the published names got no CUDA below cc 7.5 and the CUDA 13 library silently above). Every library is the c14 bytes. Scoped gates on the r2 bytes with r1 as the control: the Windows gate's cuda12 arm under the published names (r1 FAIL, r2 PASS), control, old-glibc, library identity, split-form boots (bs2, eleven2go, Mac mini), the staged-bytes gate.
+
+**c14 (2026-10-31) — a new cut.** `--version`: `llamafile v0.10.5 (opencoti-0.10.5-c14) build 2610312243001`; chain 0001–0822 (c13 r6 ended at 0717). Built in the clean-room from `release/c14`. What changes: `GET /polykv/pools` (and `/kv`, `/elastic`) shows a pool op at once — create, fork, release, pin, admission force the read snapshot (0822, bug-4304; the list could stay stale on an idle engine since c13); no admission 429 without PolyKV (0718, bug-4140); the PolyKV gate books what it admits and refuses from a measured law (0721, 0724); the admission law `t = W(total rows) + k D` with a composition-matched k and one accounting for the PolyKV and elastic gates (0773, 0777, 0812, 0818); prefill and decode steps alternate by default so one prompt never stalls the decoders for its whole length (`--pd-step-budget alternate`, 0722, 0815) with the opt-in bounded prompt step `--pd-prefill-step-ratio` (0819); a session's step reads only its own live cells on CUDA, Vulkan and Metal (0725–0731, 0762), 256-cell KV pages by default (0770); PolyKV decode reads each shared block once for all its sessions (0764–0769, −23 % at 16 sessions); the KQ mask built on the device in row chunks (0785–0789); run-time KV commits that never fail (0813) and the Windows commit guard (0814); the lazy / split pinned KVarN host arena (0756–0758); `--moe-strategy` (0739, 0740); the drafter changes (0754, 0772, 0791–0794, 0806–0808: `--auto-mtp-policy adaptive`, opt-in); the CUDA 12 legacy refusal (0792, bug-4247); LFM3 and LFM3-VL (0817); the outer llamafile 0.10.6 commits (0816); the xollama #26 fixes (0738). Features: the c13 r6 set, no new names. Gated on these bytes (bare 72d949a3cbdd): the old-glibc run gate (glibc 2.28 image, Vulkan + CUDA, every read route twice) on the side dir and again on the staged bytes; the composition smoke on the RTX 3090 (14/14, 17/17, 17/17, with the 0822 plain-pool-list check); split-form boots with an empty HOME on bs2 (CUDA, Vulkan, the forced cuda12 arm), on eleven2go (RTX 3090 CUDA and Vulkan, RX 9070 XT Vulkan: 66/66 layers on the device, needle found, 68.9 / 62.8 / 72.0 tok/s) and on the Mac mini (Metal, signed loader); the slot-lazy gate (bug-4061) CUDA 5/5, CPU 6/6, Vulkan 5/6 with the +22 MiB at default slots accepted by the owner (bug-4308); the Bonsai 2 Vulkan gate (needle 3/3 at 112k, speed, KLD 0.000305, parity at knife edges only, old-vs-new library ident); the RADV iGPU rig 4/4. The table is in RELEASE_NOTES.md.
+Feature rows: c13 r6's 73 plus four pin-only rows for xollama's capability gate (mails #2041/#2042, 2026-10-31): `arch_lfm3_v1` (0817), `vulkan_matvec_tune_v1` (0802/0803/0810, opt-in), `auto_mtp_adaptive_v1` (0807/0808, opt-in), `moe_strategy_v1` (0739/0740). /props `features` of this engine does not list them (unchanged from c13 r6); the pin is the capability source for consumers.

components/engine/2611021012001/opencoti-0.10.5-c14-2611021012001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76099ee3756332e20c5681798a3620ce983d429cc30882f02e9350de4e50590
+size 146965142

components/engine/2611021012001/opencoti-0.10.5-c14-2611021012001.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76099ee3756332e20c5681798a3620ce983d429cc30882f02e9350de4e50590
+size 146965142

components/macos/2610311711005/BUILD_INFO.macos.md

@@ -2,7 +2,7 @@
 
 Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
 
-Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2610312243001, 2611010802001, 2611011335001, 2611011619001, 2611012008001.
+Built from the engine source of build 2610312243001; gated floor (engine-min) 2610312243001; gated with 2610312243001, 2611010802001, 2611011335001, 2611011619001, 2611012008001, 2611021022001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|

components/vulkan/2611011644001/BUILD_INFO.vulkan.md

@@ -2,7 +2,7 @@
 
 Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
 
-Built from the engine source of build 2611011619001; gated floor (engine-min) 2611011619001; gated with 2611011619001, 2611012008001, 2611012031001.
+Built from the engine source of build 2611011619001; gated floor (engine-min) 2611011619001; gated with 2611011619001, 2611012008001, 2611021022001, 2611021012001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|