No article text was recorded for this version.
framework execution overhead
Version 1 of 138 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Moving Deep Learning into Web Browser: How Far Can We Go?
- Blog: The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment
- Blog: Hierarchical Roofline Performance Analysis for Deep Learning Applications
- Blog: The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment
- Blog: Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
- Blog: Time-Based Roofline for Deep Learning Performance Analysis
- Blog: Towards Pareto Optimal Throughput in Small Language Model Serving
- Blog: Exploiting Parallelism Opportunities with Deep Learning Frameworks
- Blog: Benanza: Automatic μBenchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs
- Blog: Restoring Extremely Dark Images in Real Time
- Blog: A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification
- Blog: LightSeq: A High Performance Inference Library for Transformers
- Blog: Efficient Neural Audio Synthesis
- Blog: Activation sharding for scalable training of large models
- Blog: Static Automatic Batching In TensorFlow
- Blog: Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration
- Blog: CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
- Blog: Improving Deep Learning Framework Testing with Model-Level Metamorphic Testing
- Blog: SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
- Blog: Understanding and optimizing the performance of distributed machine learning applications on apache spark
- Blog: FfDL: A Flexible Multi-tenant Deep Learning Platform
- Blog: Distributed Training Large-Scale Deep Architectures
- Blog: Densest k-Subgraph Mining via a Provably Tight Relaxation
- Blog: Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
- Blog: Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training
- Blog: HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs
- Blog: The Design and Implementation of a Scalable Deep Learning Benchmarking Platform
- Blog: StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
- Blog: Multi-Task Discriminative Training of Hybrid DNN-TVM Model for Speaker Verification with Noisy and Far-Field Speech
- Blog: MultiMax: Sparse and Multi-Modal Attention Learning
- Blog: DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
- Blog: Scaling Molecular Dynamics with ab initio Accuracy to 149 Nanoseconds per Day
- Blog: Polyline Path Masked Attention for Vision Transformer
- Blog: Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision
- Blog: Characterizing Deep Learning Training Workloads on Alibaba-PAI
- Blog: Performance Evaluation of Deep Learning Tools in Docker Containers
- Blog: Reconstructing Pruned Filters using Cheap Spatial Transformations
- Blog: Liger-Kernel: Efficient Triton Kernels for LLM Training
History & citation
Current · Permanent link
- This direction split from Overcoming Software Overhead in Deep Learning Frameworks (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_framework_execution_overhead_757acea6,
title = {framework execution overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/framework-execution-overhead/rdr_757acea684b248978e23ba562751e6a8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_framework_execution_overhead_757acea6_v1,
title = {framework execution overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/framework-execution-overhead/rdr_757acea684b248978e23ba562751e6a8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}