ml-accelerator

Here are 4 public repositories matching this topic...

NaciCankaya / Floating_point_noise_GPU_verification

Records of experiments testing the reproducibility of LLM workloads on datacenter GPUs. Key novelty: Non-associativity is a "fingerprint" of an inference stack and implementation.

gpu parallel-computing numerical-analysis proof-of-work ai-governance ai-verification ml-accelerator non-associative-addition ml-reproducibility

Updated Apr 19, 2026
Jupyter Notebook

xDarkicex / rnxa

Star

Relux Network Accelerator

metal ml ml-accelerator

Updated Jun 13, 2026
Go

rohithkancherla / igcn-fpga-accelerator

Star

I-GCN graph convolutional network accelerator on Xilinx Zynq UltraScale+ ZCU9EG. Vitis HLS 2025.1, INT8 mixed-precision, 4-PE parallelism, up to 53% pruning and 35% latency reduction over baseline GCN inference.

fpga hls xilinx quantization hardware-acceleration int8 masters-thesis graph-convolutional-network graph-neural-networks hardware-accelerator vitis-hls zynq-ultrascale ml-accelerator

Updated Mar 27, 2026
C++

JaishyamReddivari / systolic_array_dv

Star

UVM verification of an 8×8 INT8 weight-stationary systolic-array ML accelerator — closed to 100% functional coverage on an open-source Verilator + UVM toolchain.

coverage rtl systemverilog uvm verilator sva functional-verification asic-verification axi4 design-verification ml-accelerator stolic-array

Updated Jun 11, 2026
SystemVerilog

Add this topic to your repo

To associate your repository with the ml-accelerator topic, visit your repo's landing page and select "manage topics."

Learn more