Spaces:
Running on Zero
Running on Zero
Commit History
2 days ago
-
Read the kernel cache anonymously from the now-public dataset Running
Verified signature1f01791 -
Read the kernel cache with FASTH3_KERNEL_CACHE_TOKEN when set
Verified signatureThe org Space's HF_TOKEN cannot read the private multimodalart cache repo.78f528e -
Tile-64 attention and a persistent kernel cache
Verified signatureSwitch the fine sparse attention from the rtx-4090 profile's bf16 tile-128 emulator to FastVideo's Triton tile-64 block-sparse kernel (~1.3x per DiT step). Its autotune is keyed on sequence length, so every new canvas, length or reference mix re-benchmarked 12 configs (10-45 s on the first step); num_stages=5/num_warps=4 won at every measured length, so pin it. Point every JIT cache (flashinfer, Triton, inductor, CUDA, torch NVRTC) at /tmp/fasth3-kernels and restore a prebuilt archive from multimodalart/fasth3-omni-kernel-cache at startup, keyed on the torch/triton/flashinfer/fastvideo/fastvideo-kernel versions. ninja's deps log keeps nanosecond mtimes the archive can't, so restored flashinfer modules looked stale; skip the build when the module's .so exists. The first call after a boot no longer spends ~170 s compiling. GPU duration estimate follows the new timings and charges extra images and videos.798a242 -
Show per-step generation progress
Verified signatureReport progress from the GPU worker: stage starts and each denoising step via stage forward wrappers and a transformer pre-hook. The pipeline creates its stages lazily, so run post_init before hooking; FastVideo runs the forward on its own thread, so carry the Gradio context into the callback.898fc04
3 days ago
-
Build the FastVideo engine once at startup (ZeroGPU-native)
Verified signatureThe generator is now constructed at module scope on ZeroGPU's emulated CUDA: every weight FastVideo puts on "cuda" is captured and packed, the same as a diffusers .to("cuda") at startup, and each @spaces.GPU call only runs generate. The startup warmup and the per-call build are gone. FastVideo's in-process worker needed six shims to initialize without a GPU (fasth3_engine.zerogpu_main_process_shims): set_device/mem_get_info, the torch.cuda platform instead of the NVML probe, a one-rank gloo process group with the one-rank barrier skipped, safetensors read on CPU then moved with .to(), the integrated-GPU cuInit probe pinned to a discrete card, and the NVFP4 encoder's flashinfer check deferred to the first GPU call. The last two each performed a failed cuInit in the parent that every forked GPU worker inherited. Measured on a factory-rebooted copy (1344x768, 124 frames): first call after boot 359 s (kernel JIT, cached on disk), every later call 181 s end to end. GPU duration: 420 s for…b5ae9a7 -
Start with an empty composer; dim placeholders
Verified signatureThe preloaded example was set from js_on_load during mount, before the component value reached the server, so Generate on an untouched page sent no references. The page now starts empty and the example cards load one in.eb7e170 -
FastH3-Omni: Gradio 6 reference composer UI (#1)
- UI from multimodalart/FastH3-Omni: ordered image/audio/video references, upsample, FastVideo colors (e4d7fcb9045865d78f197f136a45a61de58a4884) - Gradio 6 composer: tagged references, H3 builder + free-write, upsample; rename to FastH3-Omni (c91c3f56e47c29835c7e582568c5306dceb79ff5)099efca -
Example prompts: keep reference subject, place in a new scene (OmniRef use case)
Verified signaturef3d90ec -
Example prompts aligned to the reference images (preserve subject identity)
Verified signature27889f6 -
Concise 2-sentence description (model first, then inputs)
Verified signature4f82a37 -
Warm boot: build + FP4 JIT + a warmup generation during startup GPU grant (FASTH3_WARMBOOT=0 to disable)
Verified signaturedd6ee18 -
6-section H3 prompt builder + 768p recommended default; structured examples
Verified signature1b6c5c1 -
Revert jit-cache (shim pulls unavailable sm100a dep); restore working build
Verified signaturebf9b62e -
Install flashinfer jit-cache shim + sm120f provider (skip FP4 JIT)
Verified signature00503cf -
Add prebuilt flashinfer sm120 cubins (skip FP4 JIT on cold boot)
Verified signaturef93a153 -
Populate-only examples (fix click break) + audio in closed accordion
Verified signature8845a97 -
FP8 OmniRef variant for ZeroGPU benchmark
Verified signatureb8f2c17 -
initial commit
Verified signatureb4e4214
