strata generate: PCIe probe: 28.4 GB/s host->device (best of 28.4 28.4 28.4 28.4) -> pcie_frac 0.55 (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: /workshop/bench-flashnext/packs-6f32ec07/iq3_s experts (largest blob 2.66 MB), token embedding IQ4_XS in mapped host memory (322 MiB)
strata generate: 1466 MiB of weights loaded from /workshop/bench-flashnext/packs-6f32ec07/iq3_s (302 canonical tensors skipped: served natively)
strata generate: 300 native projection matrices, 2018.88 MiB of weights
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 /workshop/bench-flashnext/strata-6f32ec07/data/expert-profile.bin: 24576 ranked pairs, built for 24576 slots
strata generate: PLE on, table 320001536 rows of /workshop/bench-flashnext/models/IQ3_S/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 0.32 s (2423 MiB/s)
strata generate: experimental native Q5_K head, 521472000 bytes
strata generate: GPU 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0
strata generate: expert arena read through the file cache (buffered (not Windows))
strata generate: expert arena: cudaHostRegister PORTABLE ok; large pages skipped (STRATA_NO_LARGEPAGES); using 4 KB pages
strata generate: loaded 46.84 GiB at 9.14 GiB/s
strata generate: expert cache auto: 87.31 GiB free, 700 MiB reserved (+86 MiB for the draft head) -> 24576 slots
strata generate: expert cache 24576 slots, 46.84 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 24576 of 24576 slots from the profile; slot 0 verified
strata generate: R4 hit path ON - resident experts are computed on the GPU
strata generate: 31 expert-pool workers + the host thread
strata generate: session is up (engine 0.1.39)
strata generate: token graph hit path: 24576 resident experts, decided on the device
strata serve: prompt chunk auto: 8192 tokens, a 384-slot ring
strata serve: the prompt path borrows 2161 CUDA0 cache slots (4.12 GiB)
strata hc: CUDA0: the hyper-connection read runs as staged (the norm per token and stream, the down projection's activations staged ahead by cp.async); checked bit for bit against the plain read on this card (STRATA_HC_SPLIT=1 or 0 for the earlier ones)
strata verify: window up to 6 tokens, 74.7 MiB of device buffers (100% VRAM resident: zero-doorbell graph)
strata mtp: draft head over 40525 tokens (81.2 MiB)
strata serve: 40948 MiB of VRAM free with everything loaded
strata verify: captured the 6-token window (upload no error, sync no error)
strata verify: captured the 1-token window (upload no error, sync no error)
strata verify: captured the 4-token window (upload no error, sync no error)
strata verify: captured the 3-token window (upload no error, sync no error)
strata verify: captured the 2-token window (upload no error, sync no error)
strata serve: prompt 4038 tokens = 0 reused + 4038 read in 1396 ms (2892.1 tok/s), 256 generated in 1281 ms (199.8 tok/s), drafts accepted 163 of 234, 1 checkpoints
strata serve: suffix drafts: 3 windows, 8 of 15 drafts accepted
strata serve: prompt 4038 tokens = 0 reused + 4038 read in 1029 ms (3924.4 tok/s), 256 generated in 1249 ms (204.9 tok/s), drafts accepted 158 of 224, 1 checkpoints
strata serve: suffix drafts: 1 windows, 4 of 5 drafts accepted
strata serve: prompt 4038 tokens = 0 reused + 4038 read in 1030 ms (3920.0 tok/s), 256 generated in 1204 ms (212.6 tok/s), drafts accepted 165 of 221, 1 checkpoints
strata serve: prompt 32038 tokens = 0 reused + 32038 read in 6364 ms (5033.9 tok/s), 256 generated in 1409 ms (181.7 tok/s), drafts accepted 147 of 231, 2 checkpoints
strata serve: suffix drafts: 4 windows, 6 of 20 drafts accepted
strata serve: prompt 32038 tokens = 0 reused + 32038 read in 6215 ms (5154.7 tok/s), 256 generated in 1355 ms (188.9 tok/s), drafts accepted 151 of 221, 2 checkpoints
strata serve: suffix drafts: 2 windows, 3 of 8 drafts accepted
strata serve: prompt 32038 tokens = 0 reused + 32038 read in 6228 ms (5143.9 tok/s), 256 generated in 1302 ms (196.7 tok/s), drafts accepted 160 of 225, 2 checkpoints
strata serve: suffix drafts: 2 windows, 2 of 5 drafts accepted
strata serve: prompt 128037 tokens = 0 reused + 128037 read in 25708 ms (4980.4 tok/s), 256 generated in 1567 ms (163.3 tok/s), drafts accepted 138 of 235, 6 checkpoints
strata serve: suffix drafts: 3 windows, 4 of 6 drafts accepted
strata serve: prompt 128037 tokens = 0 reused + 128037 read in 26087 ms (4908.1 tok/s), 256 generated in 1487 ms (172.1 tok/s), drafts accepted 149 of 241, 6 checkpoints
strata serve: suffix drafts: 2 windows, 3 of 10 drafts accepted
strata serve: prompt 128037 tokens = 0 reused + 128037 read in 26274 ms (4873.2 tok/s), 256 generated in 1439 ms (177.9 tok/s), drafts accepted 150 of 219, 6 checkpoints
strata serve: suffix drafts: 1 windows, 3 of 5 drafts accepted