Crash when starting #85

The engine crashes when loading the model. (RTX 3070 Ti 8Gb, 64GB RAM, Cuda 13.4, Driver 616.92)
I also crashes after "START-HERE.bat --calibrate". Btw, it works fine with llama.cpp (around 10-12 tk/s)

Starting qwen3.8-flash-next-iq3_s: it loads about 55 GB into RAM and locks part of it for the GPU.
While it does, YOUR PC CAN BE SLOW OR STOP RESPONDING FOR 1-3 MINUTES (longer the first time after a
restart). That is normal: please wait and don't close this window - the browser opens when it is ready.
Later, closing this window stops the model.

loading the vision encoder ...
loading the model (the first start takes a minute or two) ...
[strata] starting the engine: reading the model's weights ...
[strata] loading the experts into RAM (about 55 GB) and locking part of them for the GPU.
YOUR PC CAN BE SLOW OR STOP RESPONDING FOR 1-3 MINUTES NOW - this is normal.
Please wait and don't close this window; the browser opens when it is ready.
[strata] still starting (23 s) - please wait ...
[strata] experts loaded: 46.84 GiB at 2.24 GiB/s (30 s so far)
[strata] almost ready ...
Traceback (most recent call last):
File "G:\AI\Text\Apps\Strata\serve\server.py", line 1585, in
sys.exit(main())
~~~~^^
File "G:\AI\Text\Apps\Strata\serve\server.py", line 1518, in main
engine = StrataEngine(cfg["exe"], cfg["args"], cwd=cfg.get("cwd"), log=cfg.get("log"), env=env)
File "G:\AI\Text\Apps\Strata\serve\server.py", line 181, in init
raise RuntimeError("the engine exited before it was ready" + (f" (see {log})" if log else ""))
RuntimeError: the engine exited before it was ready (see G:\AI\Text\Apps\Strata\strata-iq3_s.log)
Press any key to continue . . .

Log file:

load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
load_hparams: more info: ggml-org/llama.cpp#16842

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 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 2.24 GiB/s
strata mtp: draft layer loaded, 835 MiB of VRAM (experts 675, dense 111)
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: 0.05 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 0.1.20)
strata serve: the prompt path allocates its own buffers (too few cache slots to borrow)
strata serve: prefill: device buffers for a chunk of 8192 tokens do not fit