[strata] 2026-10-09 01:12:27 engine started: <home>/Strata/engine/strata --serve --pack <home>/Strata-data/packs/iq3_s --native <model-dir>/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf <model-dir>/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile <home>/Strata/data/expert-profile.bin --expert-cache auto --prefill auto --spec 4 --spec-min-p 0.5 --mtp <home>/Strata-data/mtp/rt --max-context 131072 --kv int8 --control-vector-scaled <home>/Strata/data/experimental-speed-projection/Qwen3.8-Flash-Next-experimental-speed-projection.gguf:1.0 --control-vector-layer-range 4 44 --cvec-mode project --cvec-dir per-layer --remote-expert-opt
strata generate: PCIe probe: 14.1 GB/s host->device (best of 14.1 14.1 14.1 14.1) -> pcie_frac 0.39 (default 0.55)
strata generate: this CPU has no AVX-512: the expert kernels run on AVX-2 (multi-token for the i-quant gate/up rows)
strata generate: native pack: <home>/Strata-data/packs/iq3_s experts (largest blob 2.66 MB), token embedding IQ4_XS in mapped host memory (322 MiB, 1.3 s)
strata generate: 1466 MiB of weights loaded from <home>/Strata-data/packs/iq3_s in 1.6 s (302 canonical tensors skipped: served natively)
strata generate: 300 native projection matrices, 2018.88 MiB of weights, in 4.3 s
strata generate: control vector mode = project, dir = per-layer, layers 4..44 (41 steered)
strata generate: the SSD is kept awake while rows are read: one page of the table after 100 ms without a read, until 60 s after the last request (STRATA_SSD_KEEPALIVE=0 turns it off)
strata generate: profile <home>/Strata/data/expert-profile.bin: 24576 ranked pairs, built for 24576 slots
strata generate: PLE on, table 320001536 rows of <model-dir>/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf
strata mtp: draft layer loaded, 950 MiB of VRAM (experts 675, dense 111), files read in 0.69 s (1139 MiB/s)
strata generate: experimental native Q5_K head, 521472000 bytes, in 1.3 s
strata generate: GPU 0: NVIDIA GeForce RTX 5060 Ti, compute capability 12.0
strata generate: expert arena read through the file cache (buffered (not Windows))
strata generate: expert arena: cudaHostRegister PORTABLE ok; MAP_HUGETLB unavailable (needed 23983 2 MiB pages, vm.nr_hugepages=0); transparent huge pages requested (MADV_HUGEPAGE)
strata generate: loaded 46.84 GiB at 1.75 GiB/s
strata generate: CPU pool tasks/phase: 24 (automatic), participating threads: 8
strata generate: 7 pool workers on logical processors 2,4,6,8,10,12,14, the host thread on 0 (draining too) (--host-core first)
strata generate: expert cache auto: 7.84 GiB free, 700 MiB reserved (+218 MiB for the draft head) -> 2798 slots
strata generate: expert cache 3627 slots, 6.94 GiB of VRAM; policy is
strata generate: the GPU computes the experts in the cache; it rounds differently from the CPU,
                 so a reply can differ slightly from a run without the cache (same quality:
                 bench/results/2026-09-27-cache-parity).
                 PROFILE, ranked by routing frequency, no eviction.
strata generate: pre-filled 3627 of 3627 slots from the profile in 0.7 s (10537 MB/s); slot 0 verified
