Vision encoder bug: RuntimeError: the engine exited before it was ready #174

Reopening the issue #85
Was working fine on 0.1.24, now the same issue is happening on 0.1.27. "--prefill 512" doesn't fix it, "START-HERE.bat --vision cpu" also fails.

Log
strata-vision: warmed up at 1024 image tokens
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: G:\AI\Text\Apps\Strata-data\packs\iq3_s experts (largest blob 2.66 MB), token embedding type 23 in mapped host memory (322 MiB)
strata generate: 1466 MiB of weights loaded from G:\AI\Text\Apps\Strata-data\packs\iq3_s (302 canonical tensors skipped: served natively)
strata generate: 300 native projection matrices, 2018.88 MiB of weights
strata generate: KV streaming: 32768 of 65536 cells per QSA layer in VRAM, the K/V in 0.77 GiB of pinned RAM
strata generate: PLE on, table 320001536 rows of G:\AI\Text\Apps\Strata-data\models\IQ3_S\Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf
strata mtp: draft layer loaded, 835 MiB of VRAM (experts 675, dense 111), files read in 0.38 s (2045 MiB/s)
strata generate: expert arena: locked 1302 MiB via working-set minimum + VirtualLock; cudaHostRegister of the whole arena FAILED (out of memory); 47 slices pinned (45 GiB); large pages refused for 50295996416 B (GetLargePageMinimum=2097152, VirtualAlloc error 1314); using 4 KB pages
strata generate: loaded 46.84 GiB at 2.29 GiB/s
strata generate: profile G:\AI\Text\Apps\Strata\data\expert-profile.bin: 24576 ranked pairs, built for 24576 slots
strata generate: experimental native Q5_K head, 521472000 bytes
strata generate: expert cache auto: 0.00 GiB free, 700 MiB reserved -> 0 slots
strata generate: pre-filled 0 of 0 slots from the profile; slot 0 verified
strata generate: 7 expert-pool workers + the host thread
strata generate: session is up (engine 0.1.27)
strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)
strata serve: verify: needs the profile-filled VRAM expert tier (--expert-profile and --expert-cache)