JS implementation of probabilistic data structures: Bloom Filter (and its derived), HyperLogLog, Count-Min Sketch, Top-K and MinHash
High-performance KNN similarity functions in Python, optimized for sparse matrices
High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.
High performance approximate algorithms in Go (e.g. morris counter, count min, etc.)
A fast and highly accurate differentiable Top-k operator from the "Successive Halving Top-k Operator" AAAI'21 paper.
[ICML2022] Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification
Paradise of Algorithms
Filtered Top K common words with one MapReduce
ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations [AAAI-2020]
Backend agnostic batched radix-based GPU topK in Julia
hotkey is a highly configurable, high-performance, low-cost distributed cache warming framework for Spring Boot.
jigsaw sketch implementation
Algorithms for traversing spatial networks and performing top-k queries.
Collecting topk stat from big files using multiple threads [EXPERIMENT]
A single-file, JIT-compiled CUDA batch top-k with variable k and variable sequence length per row.
Implementation of greedy and beam search, as well as top-p and top-k. Analyze how varying specific parameters of decoding and sampling algorithms can qualitatively affect the generation and interpretation of NLG evaluation metrics.
Add a description, image, and links to the topk topic page so that developers can more easily learn about it.
To associate your repository with the topk topic, visit your repo's landing page and select "manage topics."