Nautilus auto-compiles math-like tensor descriptions into optimized GPU kernels, delivering up to 42% higher throughput than prior compilers on transformer models across NVIDIA GPUs.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
PagedAttention achieves near-zero waste in LLM key-value cache memory and enables 2-4x higher serving throughput than prior systems.
ObjectCache enables KV cache storage in object storage via layerwise retrieval and custom scheduling, adding 5.6% latency for 64K contexts over local DRAM on a 100 Gbps RoCE cluster.
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
TurboMind delivers up to 61% lower latency and 156% higher throughput for mixed-precision LLM inference across 16 models and 4 GPU architectures via optimized weight packing, adaptive alignment, instruction parallelism, and KV memory pipelines.
citing papers explorer
-
Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels
Nautilus auto-compiles math-like tensor descriptions into optimized GPU kernels, delivering up to 42% higher throughput than prior compilers on transformer models across NVIDIA GPUs.
-
Efficient Memory Management for Large Language Model Serving with PagedAttention
PagedAttention achieves near-zero waste in LLM key-value cache memory and enables 2-4x higher serving throughput than prior systems.
-
ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse
ObjectCache enables KV cache storage in object storage via layerwise retrieval and custom scheduling, adding 5.6% latency for 64K contexts over local DRAM on a 100 Gbps RoCE cluster.
-
TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
-
LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind
TurboMind delivers up to 61% lower latency and 156% higher throughput for mixed-precision LLM inference across 16 models and 4 GPU architectures via optimized weight packing, adaptive alignment, instruction parallelism, and KV memory pipelines.