-
Notifications
You must be signed in to change notification settings - Fork 465
All issues
Issue creation is restricted in this repository
- #1603 · SolitaryThinker opened
on Jul 15, 2026 1
Issues
is:issue state:open
is:issue state:open
Search results
[Bug] [ui/studio] Studio becomes unclickable after dismissing Create Job or creating a job
installationInstallation and setup issuesInstallation and setup issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: trainingTraining pipeline, methods, configsTraining pipeline, methods, configsStatus: Open.#1868 In hao-ai-lab/FastVideo;[Bug] fastvideo-kernel build.sh --rocm cannot configure in the rocm/pytorch 7.14.1 image
installationInstallation and setup issuesInstallation and setup issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: docsDocumentationDocumentationscope: kernelCUDA kernels, fastvideo-kernelCUDA kernels, fastvideo-kernelscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1850 In hao-ai-lab/FastVideo;[Bug] MPS generation fails when multiprocessing worker returns output tensors
installationInstallation and setup issuesInstallation and setup issuesperformancePerformance and memory issuesPerformance and memory issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1846 In hao-ai-lab/FastVideo;VAE CPU offload copies 10 GB of fp32 through pageable memory on every FastH3 Preview generation on B200
installationInstallation and setup issuesInstallation and setup issuesperformancePerformance and memory issuesPerformance and memory issuesscope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: docsDocumentationDocumentationscope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: kernelCUDA kernels, fastvideo-kernelCUDA kernels, fastvideo-kernelStatus: Open.#1839 In hao-ai-lab/FastVideo;[Feature] Add Dreamverse mode selection for T2VA, FL2VA, and Ref2VA
installationInstallation and setup issuesInstallation and setup issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: docsDocumentationDocumentationscope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1834 In hao-ai-lab/FastVideo;Support FSDP inference with precomputed quantized weights
scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: distributedSP, FSDP, USP, multi-nodeSP, FSDP, USP, multi-nodescope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: trainingTraining pipeline, methods, configsTraining pipeline, methods, configsStatus: Open.Support LoRA lifecycle operations for MXFP8 and NVFP4 inference
scope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: trainingTraining pipeline, methods, configsTraining pipeline, methods, configsStatus: Open.#1821 In hao-ai-lab/FastVideo;[Bug] VBench SceneMetric loads Qwen2.5-Omni on CPU on any non-CUDA accelerator (device_map hardcodes cuda)
installationInstallation and setup issuesInstallation and setup issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIStatus: Open.#1815 In hao-ai-lab/FastVideo;Quickstart example OOMs on 16GB-RAM free-tier environments (Kaggle, Colab)
installationInstallation and setup issuesInstallation and setup issuesperformancePerformance and memory issuesPerformance and memory issuesscope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: docsDocumentationDocumentationscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1755 In hao-ai-lab/FastVideo;[kernel] [Feature] NVFP4 QAT: fix broken measurement plumbing and build MFU foundations (pre-work for DGX Spark QAT kernel optimization)
installationInstallation and setup issuesInstallation and setup issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: docsDocumentationDocumentationscope: kernelCUDA kernels, fastvideo-kernelCUDA kernels, fastvideo-kernelscope: trainingTraining pipeline, methods, configsTraining pipeline, methods, configsStatus: Open.#1722 In hao-ai-lab/FastVideo;- Status: Open.#1713 In hao-ai-lab/FastVideo;
[Bug] MiniMax H3 text encoder needs ~97 GB resident to load a 63 GB bf16 checkpoint(FAS-494)
installationInstallation and setup issuesInstallation and setup issuesperformancePerformance and memory issuesPerformance and memory issuesplatformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: docsDocumentationDocumentationscope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1709 In hao-ai-lab/FastVideo;