perf: accelerate VAE direct 3D convolutions - #1996

* fix: preserve "token_refiner" token for MiniMax H3 LoRAs (leejet#1864)

* fix: fail with a message when MiniMax-H3 is run in img_gen mode (leejet#1863)

* feat: support INT8 ConvRot safetensors (leejet#1857)

* fix: replace free_compute_buffer with runner_done in vae (leejet#1872)

* sync: update ggml (leejet#1873)

* fix(ci): trigger builds for ggml updates

* feat: add taeh3 support (leejet#1874)

* fix: prevent gallocr hash overflow in tiny graph-cut segments (leejet#1880)

* fix: re-clamp streaming VRAM budget to currently free memory (leejet#1878)

* fix: mark graph cuts with both a prefix and a suffix (leejet#1883)

* fix: make max_order of lms sampler configurable (leejet#1885)

* fix: guard against missing sampler/scheduler names (leejet#1887)

* chore: format code

* fix: use sd_get_preview_interval() (leejet#1907)

* feat: configurable image / video compression (leejet#1909)

* feat: support standard Qwen3-VL weights for MiniMax-H3 (leejet#1910)

* feat: load scaled FP8 weights without upfront conversion (leejet#1913)

* fix: match exact weights in LLM config detection (leejet#1923)

* feat: add LTX-2.5 support (leejet#1893)

Co-authored-by: leejet <[email protected]>

* fix: correct MiniMax H3 reference audio encoding (leejet#1886)

* fix: correct MiniMax H3 audio Euler steps (leejet#1908)

* feat: use backend-native FP8 matmul when supported (leejet#1916)

* sync: update ggml

* feat: additional `--preview-interval` values (leejet#1915)

Co-authored-by: leejet <[email protected]>

* feat: support numbering for preview images (leejet#1895)

* fix: use carrier sampling for MiniMax H3 audio (leejet#1924)

* feat: generalize temporal tiling across video VAEs (leejet#1926)

* feat: prefetch streamed layers during compute (leejet#1905)

Co-authored-by: leejet <[email protected]>

* refactor: unify runner lifecycles and weight residency (leejet#1940)

* feat: add verbose logging and log-level selection (leejet#1941)

* feat: enable single-GPU auto-fit with tiered parameter placement (leejet#1942)

* fix: reuse graph cut plans across CFG passes (leejet#1943)

* refactor: split ggml extensions and move implementations to cpp files (leejet#1945)

* fix: preserve K-quantized embedding weights (leejet#1936)

* fix: correct SDXL embeddings loading (leejet#1939)

* refactor: unify model source and weight lifecycle management (leejet#1956)

* docs: reflect GGML_MAX_NAME value change in rpc docs (and in ggml_extend assert) (leejet#1950)

* refactor: split generation pipeline out of stable-diffusion.cpp (leejet#1957)

* fix: enable VAE decode tiling fallback without auto-fit (leejet#1932)

* fix: preserve BF16 embedding weights for get_rows (leejet#1959)

* fix: handle invalid option numbers (leejet#1961)

* feat: expose the loaded model version name through the public API (leejet#1962)

* feat: add SenseNova U1.5 support (leejet#1935)

* fix: reuse graph plans when scale parameters change (leejet#1963)

* feat: add linear and attention scale overrides (leejet#1964)

* feat: preserve explicit backend assignments during auto-fit (leejet#1967)

* fix: guard GPU memory capacity and propagate encoding failures (leejet#1958)

* fix: bound plain-text runs in parse_prompt_attention regex (leejet#1919)

* feat: add Wan2.2 S2V (audio+img-to-video) support (leejet#1925)

Co-authored-by: leejet <[email protected]>

* fix: validate vision projector output dim against LLM hidden size (leejet#1918)

* fix: resolve MSVC narrowing conversion warnings (leejet#1969)

* feat: Add generation parameters into video metadata (leejet#1901)

Co-authored-by: leejet <[email protected]>

* feat: support external Hugging Face tokenizer JSON files (leejet#1973)

* refactor: require external Gemma 2 and GPT-OSS tokenizers (leejet#1974)

* feat: support Brownian tree noise in all noise injection samplers (leejet#1899)

* fix: use tokenizer-specific pre-tokenization rules (leejet#1975)

* fix: remove vision_model. from ununsed tensors (leejet#1983)

* perf: eliminate temporary allocations in Philox rounds (leejet#1982)

* fix: honor flash attention flag in LLM text encoder attention (leejet#1987)

* refactor: remove obsolete unused tensor filtering (leejet#1984)

* perf: pad small attention heads to 64 for MMA Flash Attention (leejet#1992)

* perf: update ggml for faster direct convolutions (leejet#1993)

* perf: accelerate VAE direct 3D convolutions (leejet#1996)

* fix: propagate CUDA driver dependency to shared library consumers

* fix: prevent clip_preprocess center crop from exceeding the resized image (leejet#1995)

* perf: reduce CPU overhead in graph execution and sampling (leejet#1997)

* perf: parallelize host tensor elementwise and broadcast ops (leejet#1998)

* feat: support building with upstream ggml (leejet#1999)

* feat: add Qwen Image 2.1 support (leejet#1994)

* feat: restore legacy fp8 handling when building with upstream ggml (leejet#2001)

* fix: avoid passing ggml logs as format strings (leejet#2002)

* feat: add LLaDA-Image support (leejet#1968)

Co-authored-by: leejet <[email protected]>

* feat: add native CUDA SageAttention support (leejet#2005)

* fix: avoid narrowing conversion in SigVQ patch embedding and format code

* docs: update CONTRIBUTING.md

---------

Co-authored-by: stduhpf <[email protected]>
Co-authored-by: leejet <[email protected]>
Co-authored-by: LostRuins Concedo <[email protected]>
Co-authored-by: fszontagh <[email protected]>
Co-authored-by: Wagner Bruna <[email protected]>
Co-authored-by: vmobilis <[email protected]>
Co-authored-by: Piotr Wilkin (ilintar) <[email protected]>
Co-authored-by: jk212h20 <[email protected]>
Co-authored-by: assouan <[email protected]>
Co-authored-by: nan <[email protected]>
Co-authored-by: Hmission <[email protected]>
Co-authored-by: LED-M <[email protected]>
Co-authored-by: Maphist0 <[email protected]>
Co-authored-by: George <[email protected]>
Co-authored-by: Санька Четвёртый <[email protected]>
Co-authored-by: Lin Xuhao <[email protected]>
Co-authored-by: Fabrice Aneche <[email protected]>