Skip to content
View saifmb0's full-sized avatar
9 followers · 12 following
  • Al Ain University
  • Abu Dhabi
  • 21:19 (UTC +04:00)

Highlights

  • Pro

Block or report saifmb0

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
saifmb0/README.md

Pinned Loading

  1. QAttention QAttention Public

    Query guided O(N*D) linear tree attention. Up to 8x and 17x faster over sglang's FlashInfer and DeFT respectively (680 nodes). Under review

    Python

  2. pytorch/pytorch pytorch/pytorch Public

    Tensors and Dynamic neural networks in Python with strong GPU acceleration

    Python 101k 28k

  3. sparse-vits sparse-vits Public

    Tuned FlashAttention-2 kernel for short sequence pruned Vision Transformers. Up to 2.12x faster over FA2, plug and play for 12% throughput at small batch sizes (1-4) and high sparsity (50%+)

    TeX

  4. reelwise reelwise Public

    GraphQL based SEO For Instagram reels. Equipped with Turing-optimized inference pipeline including custom FusedAttention, TensorRT exports, Quantization, and VAD gating.

    Python