End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
-
Updated
Jan 8, 2026 - Python
#
torch-compile
Here are 50 public repositories matching this topic...
A native PyTorch backend for AWS Trainium with support for eager execution, torch.compile, distributed training, and custom NKI kernels
training aws machine-learning deep-learning inference pytorch nki fsdp aws-neuron trainium torch-compile dtensor
-
Updated
Oct 30, 2026 - Python
Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before teams waste days tuning configs by hand.
python cli benchmark machine-learning deep-learning gpu modal pytorch command-line-tool profiling performance-optimization ai-agents model-training mixed-precision mlops mingpt llm-agents gpu-profiling torch-compile automated-optimization
-
Updated
May 20, 2026 - Python
AWS Neuron's extension of TorchTitan that adds AWS Trainium support with TorchNeuron for training generative AI models
training aws machine-learning deep-learning pytorch nki fsdp aws-neuron trainium torch-compile torchtitan dtensor
-
Updated
Nov 11, 2026 - Python
PyTorch extension for Rebellions NPU
python machine-learning deep-learning neural-network inference pytorch npu hardware-backend ai-accelerator torch-compile rbln rebellions-ai rebellions eager-mode
-
Updated
Nov 13, 2026 - Python
How does torch.compile() achieve massive speedups despite highly optimized torch functions? See how operator fusion works!
-
Updated
Aug 3, 2026 - Jupyter Notebook
Wide-model collective ensemble system with fractal, geometric, and heavy compilation optimizations.
ai deep-learning experimental collective fractal torch pytorch ensemble geometric-shapes experimental-paradigm geometric-algorithms geometric deep-learning-framework geometric-deep-learning ai-experiments torchvision torch-geometric agentic torch-compile geofractal
-
Updated
Apr 2, 2026 - Jupyter Notebook
Optimized PyTorch/Triton MiniMax H3 video VAE for ComfyUI, with reproducible benchmarks and optional mixed INT8 acceleration—no TensorRT engine required.
cuda pytorch triton vae minimax int8 video-generation vae-implementation vae-pytorch int8-quantization comfyui torch-compile comfyui-custom-node gpt-optimization minimax-h3
-
Updated
Oct 8, 2026 - Python
Optimized CSM-1B TTS pipeline for RTX 5090 (Blackwell sm_120). CUDA graph replay via patched HF Transformers. ~0.46x RTF. Topics (tags): csm text-to-speech rtx-5090 blackwell cuda-graphs torch-compile sesame streaming pytorch
text-to-speech streaming pytorch tts sesame csm huggingface blackwell torch-compile rtx-5090 sm-120 cuda-graphs
-
Updated
Apr 5, 2026 - Python
Compression-aware Qwen3-VL inference engine with torch.compile, CUDA Graph, scaled-FP8 KV, visual compaction, and multimodal prefix caching.
-
Updated
Sep 8, 2026 - Python
Runs Triton kernels from their IR on the CPU and checks every launch (races, out-of-bounds, per-pass validation). Found silent torch.compile miscompiles without a GPU.
gpu verification pytorch triton inductor compiler-testing translation-validation mlir llm-agents torch-compile
-
Updated
Oct 24, 2026 - Python
Leveraging torch.compile to accelerate cross-encoder inference
-
Updated
Mar 3, 2025 - Python
Benchmarking, optimising and serving the TabFM tabular foundation model online: exact KV cache, torch.compile, FastAPI, Triton, KServe on kind and GKE
kubernetes machine-learning pytorch gke model-serving inference-optimization kserve nvidia-triton torch-compile claude-code nvidia-l4 tabfm tabular-foundation-model
-
Updated
Sep 16, 2026 - Python
Check that ONNX Runtime, OpenVINO, Core ML, TensorRT, ExecuTorch and torch.compile give the same results as eager PyTorch, on the values that break them
testing pytorch tensorrt coreml onnx openvino onnxruntime torch-compile executorch numerical-accuracy
-
Updated
Nov 9, 2026 - Python
Fused FP8 Triton matmul for vLLM on NVIDIA RTX Spark / GB10 (sm_121), native Windows. 13% faster than WSL2 with Gemma 4 12B.
windows cuda pytorch nvidia triton gemma batch-inference fp8 vllm local-llm llm-inference torch-compile gb10 windows-arm64 dgx-spark sm121 gemma4 rtx-spark
-
Updated
Nov 5, 2026 - Python
A PyTorch-like tensor library written in Bend2, with machine-checked laws
-
Updated
Oct 22, 2026 - Python
Distilling Florence-2 into a compact ~60M-param VQA student (feature-matching + attention transfer) — ~70% teacher-accuracy retention at 138x inference throughput with bf16 + torch.compile on H100.
computer-vision deep-learning pytorch vqa knowledge-distillation model-compression visual-question-answering inference-optimization vision-language-model florence-2 torch-compile
-
Updated
Jul 22, 2026 - Python
Evidence-gated torch.compile optimization lab with offline-verifiable bundles
-
Updated
Sep 6, 2026 - Python
Measurement-driven PyTorch training autotuner — tries precision × torch.compile × memory-format configs on your model, keeps the fastest, never returns one slower than your baseline. Honest, committed benchmarks.
performance deep-learning optimization pytorch gpu-acceleration auto-ml mixed-precision torch-compile training-speedup
-
Updated
Oct 13, 2026 - Python
Add this topic to your repo
To associate your repository with the torch-compile topic, visit your repo's landing page and select "manage topics."