BladeDISC++: A Dynamic‑Shape AI Compiler for Memory‑Peak Optimization in Deep Learning Training

The article introduces BladeDISC++, a dynamic‑shape AI compiler from Alibaba Cloud PAI, explains the memory‑peak challenges of dynamic‑shape deep‑learning workloads, describes its symbolic‑shape graph, joint compile‑time/runtime optimizations such as operation fusion, scheduling and just‑in‑time rematerialization, and presents Llama2 experiments showing significant GPU memory savings and throughput gains.

AI compilerBladeDISCLlama2

0 likes · 15 min read

BladeDISC++: A Dynamic‑Shape AI Compiler for Memory‑Peak Optimization in Deep Learning Training

Alibaba Cloud Big Data AI Platform

Dec 11, 2023 · Artificial Intelligence

How PAI‑Blade Supercharges PyTorch Training with Up to 41% Speedup

This article explains how PAI‑Blade uses compiler optimizations, TorchDynamo, MHLO conversion, and aggressive kernel fusion to accelerate PyTorch training, provides simple two‑line integration code, showcases benchmark results on A10 and A100 GPUs, and details deployment steps on PAI‑DSW.

BladeDISCGPU OptimizationPAI-Blade

0 likes · 8 min read

How PAI‑Blade Supercharges PyTorch Training with Up to 41% Speedup

Alibaba Cloud Big Data AI Platform

Dec 9, 2022 · Artificial Intelligence

What’s New in BladeDISC 0.3.0? Boosting PyTorch 2.0, GPU/CPU Optimizations, and Quantization

BladeDISC 0.3.0 introduces full PyTorch 2.0 compilation support, new TorchDynamo optimizations, extensive GPU memory‑intensive compute enhancements, Shape Constraint IR, experimental quantization across multiple hardware platforms, and a suite of compiler‑level improvements for training and inference acceleration.

BladeDISCGPU OptimizationMLIR

0 likes · 11 min read

What’s New in BladeDISC 0.3.0? Boosting PyTorch 2.0, GPU/CPU Optimizations, and Quantization

BladeDISC++: A Dynamic‑Shape AI Compiler for Memory‑Peak Optimization in Deep Learning Training

How PAI‑Blade Supercharges PyTorch Training with Up to 41% Speedup

What’s New in BladeDISC 0.3.0? Boosting PyTorch 2.0, GPU/CPU Optimizations, and Quantization

What’s New in BladeDISC 0.3.0? Boosting PyTorch 2.0, GPU/CPU Optimizations, and Quantization