Under development — I'm actively building this site.

huzama

Summary

Builds efficient long-context language models, and the systems they run on. SpotAttention makes block-sparse attention work on pretrained models, holding dense accuracy at long context and decoding 3.9× faster than FlashAttention in custom Triton kernels. Attention-Span takes the other route and lets a model declare where it will attend, cutting decode attention cost up to 53% in vLLM and FlexAttention.

Education

  • Integrated M.S./Ph.D. in Artificial Intelligence
    Korea Advanced Institute of Science & Technology (KAIST) Seoul, South Korea
    Advisors
    Se-Young Yun and James Thorne
    Thesis
    Efficient Long-Context Large Language Models
    Teaching Assistant
    Deep Learning for Natural Language Processing (Fall 2023)
  • B.E. in Computer Science and Engineering
    National University of Sciences & Technology (NUST) Islamabad, Pakistan
    Thesis
    IoT-Based Intelligent Manufacturing Execution System with Predictive Analysis
    Honors
    Medals of Excellence; Merit-Based Scholarship (2018–2020)

Research Experience

  • Graduate Researcher
    Korea Advanced Institute of Science & Technology (KAIST) Seoul, South Korea
    • Design sparse attention, KV-cache, and speculative decoding methods for long-context LLMs in the OSI Lab, from algorithm to Triton and CUDA kernel.
    • Advised eight undergraduate teams on multilingual LLM evaluation, one low-resource language each, producing BEnQA (Findings of ACL'24) and CLIcK (LREC-COLING'24).
    • Advised four undergraduate students on cultural evaluation of text-to-image and multimodal models, producing CULTDIFF (ACL'25) and MIXCUBE (C3NLP @ NAACL'25).
  • Research Intern
    RiseTech Islamabad, Pakistan
    • Built a U-Net for spinal segmentation and scoliosis classification, and a vision-language model generating diagnostic text from chest X-rays.

Selected Projects

see all
Efficient Long-Context Inference
2025 – Present
  • SpotAttention : a plug-in block-sparse selector that matches dense accuracy at long context while decoding 3.9× faster than FlashAttention.
  • Attention-Span : a prompting protocol that lets a model declare where it will attend, cutting decode attention cost up to 53% at near-zero accuracy loss.
  • Content-Aware Sparsity : prunes distractor tokens by content, not position, cutting noise as well as compute in long-context models.
Efficient-LLM Architecture & Training Systems
2023–2025
  • CascadeFormer : depth-tapered Transformers and gradient-based layer pruning motivated by Gradient Fan-in Asymmetry, cutting latency 8.6% and raising throughput 9.4% at equal perplexity.
  • Foundations of Efficient LLMs : two years of groundwork for the sparsity agenda, spanning GSPMD training on TPU pods, context compression, and uncertainty-aware prediction.

Publications

Equal contribution.

Systems & Infrastructure

2023 – Present
  • GPU Cluster : built and run a Slurm cluster of heterogeneous GPUs serving the lab's research, with unified FreeIPA identity, NUMA-aware per-job GPU isolation, shared ZFS storage over NFS, and a self-hosted WireGuard overlay connecting remote nodes.
  • HomeLab : a self-hosted cloud on Proxmox and ZFS, with pfSense routing, SSO across every service, and a local LLM stack.

Open Source

  • pytorch/xla : two merged fixes, bool dtype support for fori_loop's randint (#7632) and rank-0-only deletion in the distributed checkpoint manager (#7296).
  • huggingface/transformers : proposed the index_copy_ approach for XLA StaticCache (#31118), shipped in #31857.
  • plezy : two merged fixes to a Flutter Plex client, PGS subtitles when transcoding (#1399) and transcode-session reporting on the timeline (#1381).

Skills

LLM Training & Inference
Pretraining, Supervised fine-tuning, Reinforcement learning (PPO, GRPO), PEFT, Knowledge distillation (KL), Long-context inference, Sparse attention, KV-cache compression, Speculative decoding, Quantization
ML Systems & Performance
Distributed training (FSDP, GSPMD, RDMA), TPU/XLA static graphs, Custom attention kernels (Triton, CUDA), Roofline latency modeling
Frameworks & Tooling
Python (PyTorch, Hugging Face, vLLM, FlexAttention), Weights & Biases, Docker, ZFS / TrueNAS

BibTeX