Skip to content

Issues: kvcache-ai/Mooncake

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

29 Open 38 Closed
29 Open 38 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Potential Cache Hit Rate Reduction in Cache-Aware Scheduling
#131 opened Mar 7, 2025 by cy953708688
1
Will disaggregated vllm with MooncakeStoreConnector support TP and PP？
#127 opened Mar 5, 2025 by c-guo16
[DOCS][BUG]Can not run the examples follow vllm-integration-v0.2.md and vllm-integration.md
#124 opened Feb 28, 2025 by maobaolong
5
link warn : connection already connected
#123 opened Feb 27, 2025 by zx-ai
1
[DocsRequest]: Need vllm integration mooncake and run examples step-by-step
#122 opened Feb 27, 2025 by maobaolong
1
请问有计划提供编译构建好的容器镜像吗？
#121 opened Feb 27, 2025 by cheferrari
3
压测出现WC状态和QP错误
#117 opened Feb 22, 2025 by power-more
4
Some questions about communication time
#103 opened Feb 13, 2025 by sitabulaixizawaluduo
6
target node error
#97 opened Feb 11, 2025 by zx-ai
4
What is the communication protocol for two GPUs within the same node?
#90 opened Jan 22, 2025 by Rookie-Kai
5
Support Model
#88 opened Jan 21, 2025 by duzw9311
2
Installing error!!
#85 opened Jan 21, 2025 by IEI-mjx
4
vllm use mooncake as pipline by RDMA is not work, error message: transport retry counter exceeded
#82 opened Jan 16, 2025 by yueyuep
2
proposal: improve the topology metadata
#78 opened Jan 13, 2025 by doujiang24
2
Libfabric transport layer support
#76 opened Jan 10, 2025 by xendo
2
Questions about transfer_engine_bench
#75 opened Jan 10, 2025 by cyLi-Tiger
1
How to set protocol parameter when prefill and decode in the same node?
#68 opened Jan 7, 2025 by gujingit
2
Why do we need to disable CUDA graph (enforce_eager) for Tensor parallelism?
#64 opened Jan 6, 2025 by skyCreateXian
1
Why is ITL's first token so long?
#62 opened Jan 3, 2025 by sunshenao
3
对于p2p-store-example，用阿里云eRDMA，设置MC_GID_INDEX=1时无法启动，只有0才能启动，不过ibv_modify_qp仍然报错
#53 opened Dec 26, 2024 by power-more
2
Inquiry Regarding "Mooncake- A KVCache-centric Disaggregated Architecture for LLM Serving"
#50 opened Dec 25, 2024 by VegetaPn
16
CXL/Shared memory
#48 opened Dec 22, 2024 by stmatengss
@stmatengss
2
[RoadMap] Mooncake Roadmap Q1 & Q2 2025 Roadmap Future roadmap or plan for new features
#44 opened Dec 18, 2024 by stmatengss
4 of 40 tasks
@james0zan
8
"Address not registered by any device(s)" Error when block_size is large
#38 opened Dec 16, 2024 by c-guo16
2
vllm-integration with multi rdma devices error
#35 opened Dec 13, 2024 by junna2016
17
ProTip! no:milestone will show everything without a milestone.