Reduce default GPU duration for High Detail mode from 60s to 30s

Pad declared ZeroGPU duration with a cold-start buffer

Sync visible GPU duration slider default to Fast mode's 15s

Fix step-done log ordering vs text_encoder offload/pre-VAE-decode

Reduce default GPU duration for Fast mode from 30s to 15s

Merge branch 'main' into ja

Add VAE decode logging: pre-decode mem snapshot, tiling prediction, peak reset

Raise VAE tile threshold to HIGH_DETAIL.max_dim (2048px) to skip tiling

Bump bitsandbytes to 0.49.2 for CUDA 13.0 support

Load text_encoder as int8 (bitsandbytes) when TEXT_ENCODER_INT8_REPO is set

Merge main into ja; resolve translation conflicts

Skip text_encoder CPU offload in fast mode; type mode as an enum

Add per-phase timing to pipeline call and text_encoder offload

Speed up fast mode: lower resolution cap, skip needless VAE tiling, fewer steps

Log exception type/repr and traceback in infer() error path

Log exception type/repr and traceback in infer() error path

Correct data retention language (Japanese) to reflect automatic pruning

Correct data retention language to reflect automatic pruning

Replace vllm-flash-attn3 kernel with native SDPA cuDNN backend; wire up attn processor

Replace vllm-flash-attn3 kernel with native SDPA cuDNN backend; wire up attn processor

Merge branch 'main' into ja

Free text encoder before VAE decode and enable VAE tiling to fix OOM

Merge main into ja: apply fp8-resident transformer fix to Japanese space

Patch RMSNorm for fp8-resident weights; fix crash in prior fp8 commit

Keep transformer weights fp8-resident instead of upcasting at load

Refactor _infer_gpu into single-responsibility helper functions

Fix misleading "includes compile" log label; add first-touch instrumentation

Pin accelerate and peft to release versions instead of git HEAD

Revert NF4 quantization: this checkpoint's weights are stored fp8-native

Pin diffusers to 0.39.0 release to fix hub dependency conflict

Quantize transformer to NF4 via bitsandbytes to fix root-cause OOM

Gate full-GPU fast path on slice size; it OOMs on this Space's 47GB MIG

Try full pipeline GPU residency before falling back to cpu offload

Merge main into ja: apply Experimental-Turbo changes to Japanese space

Use sequential CPU offload instead of moving full pipeline to GPU at once

Use cudaMallocAsync allocator to fix MIG GPU CUDACachingAllocator crash

Add startup environment diagnostics (_log_env)

Load model on CPU at startup to bypass slow ZeroGPU disk packing

Pin spaces==0.50.4 to restore fast ZeroGPU inference

Set default GPU duration for high-detail mode to 40s

Set default GPU duration for high-detail mode to 30s

Set default GPU duration for high-detail mode to 30s

Fix Japanese IME exits on iPhone by checking e.isComposing

Fix Japanese IME exits on iPhone by checking e.isComposing

Remove clothing swap example from Japanese space

Replace 高解像度 with 高画質, simplify title to 高画質AI画像編集

Update Japanese space title to 高解像度AI画像編集

Handle empty dataset repo in _list_existing_files

Fix: force list_repo_tree generator inside try/except

Narrow try/except to only the list_repo_tree API call