pin v2 payload: engine 2610161651001, cuda 2610160820001, cuda12 2610141455002, sbsa 2610141455003, vulkan 2610141455004, macos 2610141455005, media 2610071902001

.gitattributes

@@ -298,3 +298,5 @@ components/engine/2610160712001/opencoti-0.10.5-c13-2610160712001 filter=lfs dif
 components/engine/2610160712001/opencoti-0.10.5-c13-2610160712001.exe filter=lfs diff=lfs merge=lfs -text
 components/cuda/2610160820001/ggml-cuda-x86_64.so filter=lfs diff=lfs merge=lfs -text
 components/cuda/2610160820001/ggml-cuda-win-x86_64.dll filter=lfs diff=lfs merge=lfs -text
+components/engine/2610161651001/opencoti-0.10.5-c13-2610161651001 filter=lfs diff=lfs merge=lfs -text
+components/engine/2610161651001/opencoti-0.10.5-c13-2610161651001.exe filter=lfs diff=lfs merge=lfs -text

components/cuda/2610160820001/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 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610160712001, 2610160746001.
+Built from the engine source of build 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610160746001, 2610161700001, 2610161651001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|
@@ -26,6 +26,10 @@ llama.cpp/ggml/src/ggml-backend-impl.h f9fdfe6bae61d1387593b40fc0f90ceee490c6a33
 llamafile/gpu_backend.h 4929c36c034b6589e88653bcb7a5c5a225743a07320f64c0857d92bdaf048208
 ```
 
+**Gated with the r4 engine 2610161700001 (2026-10-16), the same bytes as r3:** the glibc 2.28 image on bs2 PASS; the bug-4108 reproducer and greedy identity with r3 on the Linux library (RTX PRO 6000).
+
+**xOllama on these bytes (2026-10-16; xOllama dev, the pin move to r3 (owner 2026-10-16 08:51), on the published bytes of index 7c1fa53f): PASS.** eleven2go RTX 3090, the Windows DLL 68cd73b1: qwen3:8b 124.5–125.1 tok/s (r2 124.2–125.1); f16-K / q8_0-V with flash attention 127.6–127.9 tok/s, prompt ~4.2k tok/s, attention on the GPU (bug-4090 fixed; the r2 DLL: 30.9); the engine gone 852 ms after a server kill. solidPC RTX 3090, the Linux library: G3 / G4 / G5 / G6 PASS (llama3 77.4 tok/s, four slots 311.2, council 6 / 6, speech 8 / 8, video 33 frames).
+
 **c13 r3 (2026-10-16):** the Windows DLL is rebuilt with `GGML_CUDA_FA_ALL_QUANTS` (bug-4090: every Windows DLL since c10 r3 lacked it, so flash attention with K != V had no CUDA kernel and ran on the CPU), the same six generations (read from the DLL's own fatbin), from the c13 CUDA sources (no CUDA input changed since) on bs2's content-keyed wine lane; the Linux library is the c13 bytes, unchanged. Gated with the r3 engine 2610160746001: the glibc 2.28 image (Linux), greedy identity with r2 (Linux), eleven2go RTX 3090 f16-K / q8_0-V 84.8 tok/s with no CPU flash attention (the r2 DLL: 30.9).
 
 CUDA 13. Six generations (sm_75, 80, 86, 89, 90, 120); `120` is the sm_120f kernel set. Built from the clean-room tree of

components/engine/2610161651001/BUILD_INFO.engine.md

@@ -0,0 +1,54 @@
+# engine 2610161651001
+
+Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
+
+| file | platform | kind | sha256 | bytes |
+|---|---|---|---|---|
+| `opencoti-0.10.5-c13-2610161651001` | any | bin | `35f1b217f02f4a5ea5c6fa7d4663cba0ead8264128b7932e341d8d51f514689e` | 145616598 |
+| `opencoti-0.10.5-c13-2610161651001.exe` | win-x86_64 | bin | `35f1b217f02f4a5ea5c6fa7d4663cba0ead8264128b7932e341d8d51f514689e` | 145616598 |
+
+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
+```
+
+**c13 r4 dev snapshot — the development build of the c13 r4 release, for integration testing.** Engine 2610161651001 (`opencoti-0.10.5-c13`, dev channel) is built from the same source as the c13 r4 release engine 2610161700001 (chain 0001–0689; identical by content). The libraries are the r4 release index's — the r3 bytes, unchanged. This engine itself ran the glibc 2.28 route gate (Vulkan + CUDA) and the bug-4108 reproducer on bs2 (0 placeholders in 96 answers); the scoped regression gates of the release ran on 2610161700001 (see the release notes). The r3 dev snapshot was 2610160712001.
+
+What is new in r4 (chain 0689):
+
+- **No placeholder token in the output where the notice bar acts** (0689, c13 row 45.1, bug-4108). Gemma 4's 6227 `<unusedNN>` tokens are ordinary tokens in its GGUF files; with notices on, Gemma 4 26B-A4B's own copy of a notice reached the reply as `<engine_<unused29>_status output_budget="140">…` (the built-in form) or `<system_notice` with `<unused22>` inside (a request template), or as a stray `<unused30>` right after a planted notice — visible, and not hidden by a client that hides from the notice's opening. Now a placeholder (marked unused, or named `<unusedN>` / `[unusedN]`) is never sampled while the bar is on, a line may not start with any template's opening character at a prose boundary after a notice, and the line right after a planted notice gets the same bar. Measured on the release bytes (2610161700001) (bs2, Gemma 4 26B-A4B Q4_K_M, the built-in form and a self-closing template, 48 answers each): 0 placeholders and 0 copies (r3: 2 + 1 and 9 + 12), every planted notice in the text.
+
+What is new in r3 (chain 0666–0688):
+
+- **The CPU at stock llama.cpp speed** (0666–0675, 0678, 0685–0687, c13 row 41.1). Measured on the release bytes (2610160746001) against stock llama.cpp b11521, Qwen3.6-35B-A3B UD-IQ3_XXS on the CPU: EPYC 9575F 6 threads **110.2 %** (r2 92.3 %), 1 thread 107.4 % (r2 88.3 %); Mac mini (Apple M-series, Metal off) 6 threads 99.7 % (r2 81.7 %), 4 threads 97.9 % (r2 77.4 %); Ryzen 5 5600G 6 threads 102.2 % (r2 96.1 %, a noisy host); Raspberry Pi 5 (Qwen2.5-1.5B, 4 threads) 104.2 % (r2 97.3 %). The causes, each fixed with stock's own code path: cosmopolitan's `memcpy` copied backward (a forward copy replaces it); flash attention runs on the CPU as in stock (llamafile's layer turned it off); stock's tiled int8 matmul for K / IQ quant prompts; stock's Q8_0 / Q4_0 prompt kernel (with an AVX-VNNI copy); f16 V rows converted at the variant's ISA; the CPU work buffer 64-byte aligned; F16 / BF16 prompt matmuls reach stock's kernel; ARM kernels built with clang and tuned for Apple cores; IQ2_S matrix × vector on ARM through stock's kernel; no OpenMP (ggml's own threadpool, as stock's portable builds); a CPU-only engine samples on the host; on macOS a recurrent state on the CPU is f32. `--recurrent-state-type {bf16,f16,f32}` (0680).
+- **CPUSet core selection** (0671, row 41.2; a port of the owner's llama.cpp PR #6832): threads are pinned, the default pick is physical cores, no efficiency cores, one last level cache (the prompt pool gets every last level cache); Windows CPU sets across processor groups (no 64-core limit). `--cpuset on|off`, `-bco`, `-llct`, `-atc`, `--cpuset-skip-core0`. Thread placement had never run in an opencoti build (bug-4080). i5-14600K: 115.2 % of stock native, 9950X3D 103.7 %.
+- **cpp-httplib 0.60.1** (0676, 0688, row 41.3): with stock's build definitions — a request body over 8 KB without a JSON content type is accepted (HTTP 413 before, bug-4082); a realtime websocket message that arrives in pieces no longer ends the session (bug-4105).
+- **Generation notices, contract v2** (0681, 0682, 0684, row 41.4; feature `generation_notice_v2`): the request's `notices` object (steps by `at_percent` or `left`, templates with `{left}` / `{total}`), `--notice-templates FILE`, `--print-notice-config`, `/props` `generation_notice` (the templates and the spans a client hides), `timings.notices_planted`, `POST /v1/notice {key, kind: "message_waiting"}` (through the router by key). A notice is planted only at a prose boundary, never inside code, and only while 200 or more tokens of its phase are left.
+- **`num_ctx_hold`** (0683, row 41.6; feature `elastic_window_unheld_v1`): `false` sizes the window from `num_ctx` / `num_ctx_min` and releases it at the end of the request, with a `session_id` too.
+- **Tool calls keep Windows path backslashes** (0679, bug-4092).
+- **The Windows CUDA library runs flash attention with mixed K / V types on the GPU** (bug-4090): every Windows DLL since c10 r3 was built without `GGML_CUDA_FA_ALL_QUANTS`, so an f16-K / q8_0-V cache ran attention on the CPU. New cuda component 2610160820001.

components/engine/2610161651001/opencoti-0.10.5-c13-2610161651001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f1b217f02f4a5ea5c6fa7d4663cba0ead8264128b7932e341d8d51f514689e
+size 145616598

components/engine/2610161651001/opencoti-0.10.5-c13-2610161651001.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f1b217f02f4a5ea5c6fa7d4663cba0ead8264128b7932e341d8d51f514689e
+size 145616598

components/macos/2610141455005/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 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610141255001.
+Built from the engine source of build 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610141255001, 2610160746001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|
@@ -34,6 +34,8 @@ ABI `loader` = `d6ff34022f1d3fb5af56ca0c80e3f4e552bf09f1bebdf0cb5f314a454bf38dbc
 
 Apple notarisation (Accepted), submission id(s): `ca3dd0d1-2833-4a85-8aee-71b39952c641 eea7c66d-e8a4-4860-b9da-71e9416a2805`.
 
+**xOllama on these bytes with the r3 engine 2610160746001 (2026-10-16; xOllama dev, the pin move to r3 (owner 2026-10-16 08:51), on the published bytes of index 7c1fa53f): PASS.** Mac mini, Metal, 512 tokens, 4 sampled runs + 1 greedy: qwen2.5:1.5b 122.2–124.0 tok/s (r2 123.1–128.8), llama3 30.3–30.6 (r2 31.6–31.9), qwen3.5:2b 60.5–62.1 (r2 61.7–63.6), 1–4 % under r2, within the host's run-to-run spread; every layer on the GPU, the Metal library's `ggml` digest bac5050d matching, 0 crash lines; speech 7 / 7.
+
 The prebuilt APE loader (the c12 file, `loader` digest unchanged) and a NEW prebuilt Metal library, built on the Mac by the
 c13 engine from its embedded sources (0659: reserved shared buffers). Notarised: Metal library
 ca3dd0d1-2833-4a85-8aee-71b39952c641 (Accepted), loader eea7c66d-e8a4-4860-b9da-71e9416a2805.

components/media/2610071902001/BUILD_INFO.media.md

@@ -2,7 +2,7 @@
 
 Component of the opencoti pin format v2 (docs/protocols/PIN_FORMAT.md).
 
-Built from the engine source of build 2610071819001; gated floor (engine-min) 2610040950001; gated with 2610050707001, 2610071819001, 2610100921001, 2610100940001, 2610101328001.
+Built from the engine source of build 2610071819001; gated floor (engine-min) 2610040950001; gated with 2610050707001, 2610071819001, 2610100921001, 2610100940001, 2610101328001, 2610160746001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|
@@ -32,6 +32,8 @@ llamafile/oc-codec/oc_codec_sidecar.h f2c9001d1414aa2a55533b867b79c52a52c682558e
 
 Apple notarisation (Accepted), submission id(s): `83ee464c-3816-4b5c-9da7-cd4313840f25 aa53f9d9-14ba-443a-a059-64f82416f86a`.
 
+**xOllama with the r3 engine 2610160746001 (2026-10-16; xOllama dev, the pin move to r3 (owner 2026-10-16 08:51), on the published bytes of index 7c1fa53f): PASS.** solidPC (Linux, RTX 3090): speech 8 / 8, wan2.2 video 33 frames. Mac mini: speech 7 / 7 (Kokoro x2, Supertonic x2, KittenTTS, OuteTTS x2), each transcribed back. Windows: not reported.
+
 The twelve sidecars of c11, unchanged (same `media` digest): oc-codec, oc-audiocpp, oc-espeak, three per platform.
 Not re-gated as a set at this cut (same bytes, same digest).
 

components/vulkan/2610141455004/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 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610141255001, 2610141633001, 2610160746001, 2610160712001.
+Built from the engine source of build 2610141255001; gated floor (engine-min) 2610141212001; gated with 2610141255001, 2610141633001, 2610160746001, 2610161700001, 2610161651001.
 
 | file | platform | kind | sha256 | bytes |
 |---|---|---|---|---|
@@ -26,6 +26,10 @@ llama.cpp/ggml/src/ggml-backend-impl.h f9fdfe6bae61d1387593b40fc0f90ceee490c6a33
 llamafile/gpu_backend.h 4929c36c034b6589e88653bcb7a5c5a225743a07320f64c0857d92bdaf048208
 ```
 
+**Gated with the r4 engine 2610161700001 (2026-10-16), the same bytes as r3:** the glibc 2.28 image on bs2 PASS; the Linux library.
+
+**xOllama on these bytes with the r3 engine 2610160746001 (2026-10-16; xOllama dev, the pin move to r3 (owner 2026-10-16 08:51), on the published bytes of index 7c1fa53f): PASS.** eleven2go (Windows 11): RX 9070 XT, pinned by name, 100.5–103.3 tok/s, 103.9 after 120 s loaded idle, the card OK, 0 LiveKernelReports; Radeon iGPU 5.0 tok/s, 37 / 37 layers. The Linux library: not run by xOllama for r3.
+
 Built from the clean-room tree of chain 0662. Carries the reserved (sparse) buffers of 0659: the default slots cost nothing
 until used.
 Gated with the 2610141255001 engine: the Vulkan cases of the bs2 56 / 56 gate (KLD 0.000311 against the CUDA base, needle 3 / 3 at 112k; two non-Bonsai models BIT-IDENTICAL between the c12 library and this one); the slot gate on Vulkan 6 / 6 (GPU 0 only); the glibc 2.28 image; the Windows DLL on eleven2go (RTX 3090): 64 tokens at 48.4 tok/s, the memory on the adapter the counter names, no debug-level line without -lv.