cd/entity/Rasuljanov Muhammadali· home› entities› Rasuljanov Muhammadali
grep -l @rasuljanov muhammadali /news/*.json | wc -l → 1

Rasuljanov Muhammadali

mentions 1 type Person feed RSS

// recent coverage 1 mentions

06:39
2026-07-31
github.com
artificial-intelligence

HexCore: Low-Latency Paged KV Cache Allocator in C++20 and CUDA

HexCore, a low-latency paged KV cache allocator for LLM inference written in C++20 and CUDA, has been released under the Apache License 2.0 by Rasuljanov Muhammadali. The CPU-side allocator and relate…

// co-occurs with top 7 entities
HexCore 1 vLLM 1 PagedAttention 1 FlashAttention 1 TensorRT-LLM 1 PyPI 1 Apache License 2.0 1
// topics top 4 topics
artificial intelligence 1 large language models 1 ai infrastructure 1 ai research 1