UbiquitousLearning / Mandheling-DSP-TrainingLinks
The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]
☆19Updated 2 years ago
Alternatives and similar repositories for Mandheling-DSP-Training
Users that are interested in Mandheling-DSP-Training are comparing it to the libraries listed below
Sorting:
- Automatic Mapping Generation, Verification, and Exploration for ISA-based Spatial Accelerators☆112Updated 2 years ago
- LLM Inference analyzer for different hardware platforms☆74Updated 3 weeks ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆52Updated last year
- ☆79Updated 2 years ago
- Artifacts of EVT ASPLOS'24☆26Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 10 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- LLM serving cluster simulator☆106Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆48Updated 3 months ago
- ☆21Updated last year
- DietCode Code Release☆64Updated 2 years ago
- MobiSys#114☆21Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- Summary of some awesome work for optimizing LLM inference☆77Updated 3 weeks ago
- ASPLOS'24: Optimal Kernel Orchestration for Tensor Programs with Korch☆37Updated 3 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated 2 weeks ago
- ☆92Updated 2 years ago
- ☆38Updated 11 months ago
- ☆154Updated 11 months ago
- ☆99Updated last year
- play gemm with tvm☆91Updated last year
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆121Updated 3 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆49Updated 7 months ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- ☆98Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆27Updated 4 months ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆110Updated 6 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆50Updated 11 months ago
- ☆13Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago