gemv

Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

An implementation of SGEMV with performance comparable to cuBLAS.

PCCX™ specification, documentation, and ecosystem coordination hub for open AI accelerator IP.

Matilda is a library to repeatedly multiply a constant matrix with a variable vector

Highly optimized DGEMV on CPU with both serial and parallel performance better than MKL and OpenBLAS.

High-performance FP32 GEMV for AMD RDNA 3 (gfx1100), with reproducible performance and numerical analysis.

PCCX™ v002 IP-core package — board- and model-agnostic reusable RTL for LLM, Vision, Voice, and common subsystems.

Measure and visualize why LLM inference is slow: bottleneck analysis, model dissection, KV-cache, GEMM/GEMV, quantization, and memory-bound decoding.

Hand-written CUDA kernels for batch-1 LLM decode: FP16 GEMV and online softmax at the measured memory-bandwidth limit, INT4/INT8 dequant GEMV turning compression into throughput. Nsight-profiled, correctness-gated.

🧮 CereMath is a library of Machine Learning kernels for the Wafer Scale Engine (WSE) from Cerebras. Made as a BSc thesis project

InfiniTensor 训练营作业：OpenCL Q8_0 量化 GEMV 优化（RTX 4090 D 实测）

Benchmark workbench for MAX (Mojo) LLM decode kernels vs llama.cpp / cuBLAS / FlashInfer and the memory roofline on consumer NVIDIA GPUs (sm_86/sm_89). A public record, not a competing kernel library.