Open Issues Need Help
View All on GitHub Emit worker stats 10 months ago
enhancement good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm
Support data placement module 10 months ago
enhancement good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm
Remove deprecated code for TCP/IP disk backend 10 months ago
enhancement good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm
Add support for multi-tiered caching 10 months ago
enhancement good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm
Support test bench for local performance 10 months ago
enhancement good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm
Add user friendly READMEs for each submodule 10 months ago
documentation good first issue
A high-performance RDMA backed distributed cache to address the challenges of AI training and inference.
C++
#big-data#cpp#cuda#distributed-cache#gpu#infiniband#kv-cache#python#rdma#ucx#vllm