Exact

Exact Union RegExp

Raffaele 10af539a63 feat: prefill on the NPU, decode on the CPU (--prefill-device), in the release APK (#200) ... Wide prefill graphs run on the Hexagon NPU through a two-layer arena streamed from flash; decode stays on the CPU. The app offers it in its own NPU section, off by default, Snapdragon only. A missing or unopenable device leaves the run on the CPU. release-apk builds the Hexagon backend and a skel per NPU generation in a separate, secret-free job. Bundles the llama.cpp bump to bmoe/expert-ready-hook-2609 (K-quants on the NPU). App 0.26.0 (41).		2026-09-28 09:52:46 +02:00
..
bench-analyze.py	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-lib.ps1	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-matrix-rework.ps1	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-matrix.ps1	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-pr23-c2000.ps1	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-pr23-summary.py	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-prefetch.ps1	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00
bench-report.sh	fix(scripts): bench-report model size and storage probe (du on the raw path) (#194)	2026-08-31 12:48:09 +02:00
bench-run.sh	Mark the two doc-invoked host scripts executable (#164)	2026-08-25 11:41:24 +02:00
bench-warmonly.sh	Mark the two doc-invoked host scripts executable (#164)	2026-08-25 11:41:24 +02:00
build-android.ps1	build(android): stage an explicit library list, and force GGML_OPENCL off (#124)	2026-07-28 15:10:49 +02:00
build-hexagon-android.sh	feat: prefill on the NPU, decode on the CPU (--prefill-device), in the release APK (#200)	2026-09-28 09:52:46 +02:00
build-host.sh	Mark the two doc-invoked host scripts executable (#164)	2026-08-25 11:41:24 +02:00
decode-analyze.py	feat(trace): add layer-granularity compute trace (--compute-trace-layers)	2026-07-19 09:21:39 +02:00
gptoss-matrix.sh	Mark the two doc-invoked host scripts executable (#164)	2026-08-25 11:41:24 +02:00
gptoss-mmap.sh	Mark the two doc-invoked host scripts executable (#164)	2026-08-25 11:41:24 +02:00
humaneval-bench.py	feat(moe): cache-aware expert substitution (--expert-substitute, experimental) and --ppl (#171)	2026-08-29 10:13:47 +02:00
inspect-hf-moe-release.py	feat(moe): Qwen3.8-Flash-Next support (#172)	2026-08-28 10:07:43 +02:00
make-tiny-moe.py	feat(moe): Nemotron 3.5 (nemotron_h_moe) and Ornith 1.5 support (#203)	2026-09-28 09:34:42 +02:00
route-analyze.py	feat(moe): --drop-cold-experts — spend quality only where it buys I/O (#95)	2026-07-22 17:21:55 +02:00
route-drop-replay.py	feat(moe): --drop-cold-experts — spend quality only where it buys I/O (#95)	2026-07-22 17:21:55 +02:00
route-replay.py	fix(tools): make the diagnostics fail instead of reporting a confident wrong number	2026-07-20 12:25:58 +02:00
route-viewer.py	feat(scripts): route-viewer.py — read a route trace without a spreadsheet	2026-07-15 09:52:09 +02:00
stage-hexagon-jnilibs.ps1	feat: prefill on the NPU, decode on the CPU (--prefill-device), in the release APK (#200)	2026-09-28 09:52:46 +02:00
tinymmlu-bench.py	feat(moe): cache-aware expert substitution (--expert-substitute, experimental) and --ppl (#171)	2026-08-29 10:13:47 +02:00
trace_io.py	chore(scripts): consolidate the bench drivers, prune the retired framing	2026-07-17 10:41:13 +02:00