GeezerVison is showing github.com — flashserve
Pinned
Loading
Prefix-Aware Attention for LLM Decoding
Python
49
3
An Open-Source RAG Workload Trace to Optimize RAG Serving Systems
Python
40
4
Repositories
Loading
Type
All
Public
Sources
Forks
Archived
Mirrors
Templates
Language
Sort
Showing 6 of 6 repositories
flashserve/flash-linear-attention-npu's past year of commit activity
Mosaic
Public
[ICML'26] MOSAIC: Unlocking Over 30× Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak Taming
flashserve/Mosaic's past year of commit activity
Python
9
Apache-2.0
0
0
0
Updated Nov 8, 2026
ReWY
Public
Faster Gradient Computation for Delta-Rule Attention Family
flashserve/ReWY's past year of commit activity
Python
10
MIT
0
0
0
Updated Nov 3, 2026
OLED-MoE
Public
Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading
flashserve/OLED-MoE's past year of commit activity
Python
8
0
0
0
Updated Sep 30, 2026
RAGPulse
Public
An Open-Source RAG Workload Trace to Optimize RAG Serving Systems
flashserve/RAGPulse's past year of commit activity
Python
40
MIT
4
0
0
Updated Sep 1, 2026
PAT
Public
Prefix-Aware Attention for LLM Decoding
flashserve/PAT's past year of commit activity
Python
49
MIT
3
0
0
Updated May 26, 2026