-
Notifications
You must be signed in to change notification settings - Fork 410
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] Prompt completely ignored in MLX runtime (Apple Silicon) - identical outputs across different prompts, confirmed on QAD-1.3B and FP8-1.3B
performancePerformance 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.#1736 In hao-ai-lab/FastVideo;[bug] Qwen3-VL vision tower diverges from transformers 5.15.0: visual-token embeddings mismatch (image/video conditioning parity broken on main)
platformPlatform-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, CLIStatus: Open.#1733 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;[Bug] HunyuanVideo 1.5 I2V cannot run: image_embeds is never populated, stage verification fails
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: distributedSP, FSDP, USP, multi-nodeSP, FSDP, USP, multi-nodescope: docsDocumentationDocumentationscope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIscope: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)scope: trainingTraining pipeline, methods, configsTraining pipeline, methods, configsStatus: Open.#1692 In hao-ai-lab/FastVideo;[RFC]: Command "dreamverse-server --host 0.0.0.0 --port 8009": GPU 0 warmup failed
installationInstallation and setup issuesInstallation and setup issuesscope: 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.#1685 In hao-ai-lab/FastVideo;[ci] [dashboard]: add explicit benchmark cohort comparison mode
platformPlatform-specific (Windows/macOS)Platform-specific (Windows/macOS)scope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)Status: Open.#1636 In hao-ai-lab/FastVideo;[ci] [dashboard]: add advanced hardware and software profile filters
installationInstallation and setup issuesInstallation and setup 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.#1635 In hao-ai-lab/FastVideo;[ci] [dashboard]: replace automatic all-cohort trend rendering with a cohort overview
performancePerformance and memory issuesPerformance and memory issuesscope: attentionAttention backends (VSA, STA, Flash, etc.)Attention backends (VSA, STA, Flash, etc.)scope: inferenceInference pipeline, serving, CLIInference pipeline, serving, CLIStatus: Open.#1634 In hao-ai-lab/FastVideo;[ci] [dashboard]: add exact benchmark cohort selection and clarify configuration identity
installationInstallation and setup issuesInstallation and setup 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.#1633 In hao-ai-lab/FastVideo;[ci] [Feature] Add DGX Spark (GB10) performance baseline and CI stress coverage
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: modelModel architecture (DiTs, encoders, VAEs)Model architecture (DiTs, encoders, VAEs)Status: Open.#1632 In hao-ai-lab/FastVideo;