Niko1221 146df3c468 setup.py run(): the app's installer also runs the bundled Mac preparation tools in metal/tools (metal_repack.py, stream_experts.py); a fresh Mac Terminal or app install of UD-Q4_K_XL or UD-IQ4_XS-v31 stopped with "only runs its bundled preparation tools" since af1ffd913. Test: they run, and -m, another interpreter and other folders are still refused

2026-11-07 01:29:36 +01:00

..

core

Run manifest (lite): STRATA_MANIFEST=<file> writes the selected fast paths, fallback reasons, tensor formats, engine choice and budgets as JSON (P0.1)

2026-11-06 00:21:53 +01:00

cuda

prefill_fused_iq_test: skip the Q5_0 down pairs where the native kernels do not cover them (CUDA has none; the gfx12 / gfx1151 builds run them); --only=NAME still insists

2026-11-06 16:29:26 +01:00

data

Two GTX 1080s are a working PC: an 8 GB card starts Off only beside a bigger card, and a PC whose only NVIDIA cards are Pascal uses them on the CUDA 12 engine (#3655)

2026-10-22 13:47:41 +02:00

desktop

setup.py run(): the app's installer also runs the bundled Mac preparation tools in metal/tools (metal_repack.py, stream_experts.py); a fresh Mac Terminal or app install of UD-Q4_K_XL or UD-IQ4_XS-v31 stopped with "only runs its bundled preparation tools" since af1ffd913. Test: they run, and -m, another interpreter and other folders are still refused

2026-11-07 01:29:36 +01:00

dsv41

DeepSeek engine: an expert profile of another model's size is not read; the router tests run with 192 experts and poisoned padding (CUDA, Metal)

2026-11-01 19:18:48 +01:00

fixtures

catalog: Unsloth v3.1 Qwen3.8-Flash-Next sets (UD-IQ1_M, UD-Q2_0, UD-IQ2_XS, UD-Q2_K_XL, UD-IQ3_XXS, UD-Q3_K_XL, UD-IQ4_XS-v31) at d9620119 with a per-model revision; UD-Q4_K_XL's four-shard layout accepted from local files; manual-load refusal lifted (UD-IQ1_S stays refused); mac_fit switch for the Q5_0 down sets; header-only fixtures and tests (about lines pending wording)

2026-11-05 07:23:41 +01:00

gdn

GDN: production-linked parity/bench harness, dispatch probe, FP64 fixtures, contract doc; opt-in STRATA_GDN_TC on 99-KB cards (split v/T/P buffering)

2026-10-30 01:12:19 +01:00

hip

MMQ parity screen: skip the trellis types when the ggml has no host traits for them (it read past the type table on Windows)

2026-11-05 08:06:52 +01:00

ngram

PLE reader: issue() folds a small batch in a stack buffer instead of a hash table and a job vector (P1.6)

2026-11-06 00:12:28 +01:00

platform

Windows: an engine started from a low-priority program no longer reads its model at Low disk priority; its disk priority goes back to Normal and one plain line says so (#4733)

2026-10-31 13:01:12 +01:00

prefill

Exact two-pass QSA prompt selection (opt-in STRATA_SELECT_TWO_PASS=1)

2026-11-06 15:47:43 +01:00

program

Transfer completion: flag B stays behind queued copies, and the adaptive-copy range covers the whole round (P1.1)

2026-11-05 23:39:06 +01:00

split

Run manifest (lite): STRATA_MANIFEST=<file> writes the selected fast paths, fallback reasons, tensor formats, engine choice and budgets as JSON (P0.1)

2026-11-06 00:21:53 +01:00

sycl

SYCL server: the engine_args wrapper takes the base signature (exe, announce) and forwards it (#5086)

2026-11-04 10:38:22 +01:00

terminal

Version 0.2.12 / engine 0.1.58: Terminal and app 0.2.12, Control and every engine package 0.1.58 (the 0.2.11 bump list, plus the v0.1.58 line in the setup.py version history)

2026-11-06 19:21:19 +01:00

time_skip

Time-skip and tune job records are replaced with a wait for a reader (Windows 'Access is denied' when the host reads the file at that moment: it ended jobs at random)

2026-10-16 13:29:12 +02:00

tuning

Merge f-0213-life (final 576d06553) into f-0213-int

2026-11-04 12:24:01 +01:00