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 20 public repositories matching this topic...
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
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
Aug 7, 2026 - Python
How does torch.compile() achieve massive speedups despite highly optimized NumPy 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 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
Leveraging torch.compile to accelerate cross-encoder inference
-
Updated
Mar 3, 2025 - Python
Compression-aware Qwen3-VL inference engine with torch.compile, CUDA Graph, scaled-FP8 KV, visual compaction, and multimodal prefix caching.
-
Updated
Aug 5, 2026 - Python
🚀 2-4x faster PyTorch training with one line of code. Beats torch.compile by 79%. Zero config, automatic hardware optimization for T4/V100/A100/H100 GPUs.
performance deep-learning optimization pytorch gpu-acceleration auto-ml mixed-precision torch-compile training-speedup
-
Updated
Jul 25, 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
Profile-first CUDA lab for killing GPU pipeline bubbles: stream overlap, CUDA Graphs, torch.compile, spec-decode overlap — Nsight-verified
performance-engineering gpu cuda pytorch inference-optimization microbenchmark speculative-decoding gpu-profiling torch-compile cuda-streams cuda-graphs nsign-systems
-
Updated
Jul 18, 2026 - Python
Profiling CUDA Graph vs torch.compile vs eager decode on RTX 2070 — measuring per-token latency reduction across batch sizes, sequence lengths, and GPT-2 model sizes.
python performance-engineering benchmarking gpu cuda pytorch transformer triton profiling gpt2 llm-inference cuda-graph torch-compile decode-latency staticcache
-
Updated
Jul 17, 2026 - Python
PyTorch 2.9 + HIP/ROCm learning notes: dispatcher, accelerator backend, profiler, TorchInductor, runtime, GEMM, and C++ extensions.
-
Updated
Jul 20, 2026 - Python
GPU systems benchmark comparing PyTorch eager execution and torch.compile across common deep learning operations. Measures execution time, throughput, TFLOPS, memory bandwidth, and kernel-level speedups through a reproducible benchmarking pipeline and publication-ready visualizations.
-
Updated
Jun 29, 2026 - Jupyter Notebook
PyTorch GPU inference performance exercises: roofline analysis, decode-loop profiling, KV-cache optimization, torch.compile, and CUDA graphs.
performance gpu cuda inference pytorch profiling roofline kv-cache llm-inference h100 torch-compile cuda-graphs
-
Updated
Jun 26, 2026 - Jupyter Notebook
Three measured notebooks on GPU inference optimization: roofline analysis, KV-cache decode optimization (4.21x), and CUDA-graph launch-overhead elimination (5.38x). Pure PyTorch.
gpu pytorch performance-optimization inference-optimization kv-cache llm-inference torch-compile roofline-analysis cuda-graphs
-
Updated
Jul 7, 2026 - Jupyter Notebook
Plain English + a PyTorch reference → a verified, benchmarked CUDA kernel you can pip install and torch.compile.
performance-engineering gpu cuda pytorch nvidia code-generation cuda-kernels gpu-computing claude cuda-programming llm llm-agents torch-compile kernel-generation kernelbench
-
Updated
Aug 2, 2026 - Python
One instrumentation engine for PyTorch training, two products: a fault injection tested health monitor (NaN, gradient explosion, stall, with diagnosis and ranked remedies) and a throughput sweeper (batch size, precision, DataLoader, torch.compile) with auditable bottleneck verdicts. 1.90% overhead.
python benchmarking machine-learning performance deep-learning gpu cuda pytorch nvml performance-analysis profiling anomaly-detection mlops torch-compile ml-englineering
-
Updated
Aug 3, 2026 - Python
A torch.compile backend that pays attention: custom FX fusion passes, a Triton LayerNorm kernel, and a persistent compile cache. Apache-2.0 free core of the g2n platform.
machine-learning compiler gpu cuda inference pytorch quantum-computing triton quantization quantum-simulator kernel-fusion llm local-llm torch-compile
-
Updated
Jul 27, 2026 - Python
Improve this page
Add a description, image, and links to the torch-compile topic page so that developers can more easily learn about it.
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."