Skip to content
GitLab
Explore
Sign in
educg-net-48534-3136859
project59内存受限环境的大语言模型推理优化
Repository
Branches
Overview
Active
Stale
All
main
default
protected
550554e2
·
Merge branch 'moe' into main
·
Aug 12, 2026
ahkvm
d59e28b0
·
Add unfinished OS finals presentation
·
Aug 12, 2026
moe
799f7e13
·
moe LRU experts switch
·
Aug 08, 2026
FlexInfer-v4.0
aa297ab6
·
doc: add sophomore grade to team members on cover page
·
Jun 18, 2026
sharegpt-cgroup-latency-bench
c9d73d06
·
scripts: add native macOS ShareGPT benchmark runner
·
Jun 11, 2026
lazy-kvcache
62fee6c2
·
add source code list
·
Jun 08, 2026
FlexInfer-v3.0
501ce8f4
·
Asynchronous Prefetching with layer streaming
·
Jun 07, 2026
FlexInfer-v2.0
b8d2a753
·
do prefetch works
·
Jun 05, 2026
zbm-flexinfer-experiments
dc3e883b
·
Validate runtime prefetch eviction under memory limits
·
May 28, 2026
FlexInfer-v1.0
2b3789ad
·
new feature: based on paper FlexInfer
·
May 21, 2026
measure
7c3169af
·
add a python measure script
·
May 17, 2026