Ship portable CPU dispatch and verified shared runtime dependencies

This commit is contained in:
karl committed 2026-10-12 22:35:34 +02:00
1 parent 278b09f82c
commit 0bba1a0aa7
19 files changed
+675 -17

No files matched your search

+29
View File
@@ -7,6 +7,35 @@ and `SEARCHI_FORCE_CPU=1`.
## Current integration checkpoint (2026-10-12)
The normal Windows x64 package now includes baseline and optimized CPU DLLs
with CPU/OS feature checks, plus the Vulkan backend. Shared DLLs use a common
MSVC CRT: a first `/MT` prototype crashed because model file handles crossed
separate CRT instances; the corrected `/MD` package passes real-model startup.
All 25 runtime DLLs and the worker have their non-Windows PE imports satisfied
by packaged files. Windows system UCRT/WinRT and WebView2 remain platform
requirements. This is dependency inspection, not clean-machine certification.
Both extracted-archive tests passed: automatic CPU dispatch selected
`ggml-cpu-cascadelake.dll`, and removing optimized modules from the temporary
extraction selected `ggml-cpu-x64.dll`. Both produced genuine normalized 768d
Google code vectors, started FFprobe, verified all 39 listed files, and confirmed
the Vulkan module was not loaded. The unsigned archive is 145,196,878 bytes;
its digest is recorded in [dispatch evidence](evidence/windows-package-cpu-dispatch.json)
and [baseline evidence](evidence/windows-package-cpu-baseline.json).
Recorded startup/query/exit times are diagnostic smoke samples, not comparable
benchmarks: cache state and concurrent checks differ. Baseline inference on
this modern VM does not certify older physical CPUs or operating systems.
Three builder, five staging and eleven archive regression tests passed.
Two real Google code tests and two text-reference/tail/debug parity tests also
passed using the new shared worker in forced-CPU mode. Text reference cosine
similarities range from 0.99983106 to 0.99993036; debug/normal query cosine is
1.00000000. These verify runtime equivalence, not broad retrieval quality.
The genuine Google media parity test also passed on this shared CPU runtime:
image budgets 280/140/70 and the speech fixture all meet the 0.999 reference
cosine threshold. Image/audio quality limitations and GPU gates remain open.
The following evidence describes the earlier static worker checkpoint:
The Windows-x64 universal worker built with CPU and Vulkan enabled, using the
pinned official LunarG 1.4.363.0 SDK (download hash and publisher signature
verified). Copy-only installation and later provenance/swap validation ran in