Repository files navigation
Hi there, I'm Azimbek π
Senior Machine Learning Engineer
π I'm currently working on AI & Machine Learning projects
π± I'm exploring Deep Learning, NLP, and Computer Vision
π‘ Passionate about Fintech + AI intersections
π Based in Tashkent, Uzbekistan
π¬ Ask me about Python, ML pipelines, and AI systems
π« Reach me at: LinkedIn & azimbekolimbekov1@gmail.com
Project
Description
Tech
π Trellis-WebGPU
3-bit trellis-quantized 8B LLM running a full forward pass in-browser on WebGPU β no CUDA
Python, WebGPU, WGSL
β‘ Triton Kernels
High-performance GPU kernels for LLM inference (RMSNorm, SwiGLU, W4A16/W8A16 GEMMs, fused MoE)
Python, Triton, CUDA
π¬ Agent Quality Inspect
User-aware evaluation of agentic AI systems: subgoal metrics (AUC, PPT, pass@k) + automated error analysis
Python, Agent Eval, LLM
β±οΈ Adaptive Test Time Compute
Per-instance test-time compute scaling for LLM reasoning via consensus-based adaptive sampling
Python, GSM8K, Consensus Sampling
You canβt perform that action at this time.