AI Compiler Engineer @ 10xEngineers | LLM Inference Optimization|Computer Architecture
I specialize in bridging the gap between hardware and software to accelerate AI workloads. My focus is on the RISC-V Software Ecosystem (RISE), creating high-performance kernels for LLM inference.
- π Currently working on: RISC-V Vector (RVV) support for llama.cpp and implementing LLM ops kernels for RISC-V vector extension.
- π Education: BS Electrical Engineering from UET Lahore (Gold Medalist, Rank 1/200).
- π οΈ Tech Stack: C/C++, Python, Machine Learning, RISC-V Assembly, SystemVerilog, FPGA (Vivado).
- π« Connect: LinkedIn | Email
Recent commits optimizing for RISC-V:
- af237f302 ggml-cpu: add RVV repack GEMM and GEMV for quantization types (#19121)
- b908baf18 ggml-cpu: add RVV vec dot kernels for quantization types (#18784)
- d34d5ca1e llamafile: add rvv support for sgemm kernels (#18199)
- f716588e6 ggml-cpu: extend support for RVV floating-point kernels (#17318)
- fbaa95bc2 ggml-cpu: add RVV vec dot kernels for quantization types (#18859)