-
### Search before asking
- [X] I had searched in the [issues](https://github.com/apache/doris/issues?q=is%3Aissue) and found no similar issues.
### Description
apiVersion: v1
data:
instance.co…
-
### Motivation.
There are more and more use cases, where we need to transfer KV caches between vLLM instances, or store KV caches for future use. Some concrete use cases:
- Disaggregated prefilling.…
-
After running block `20240052` batching 50 transactions, in the first segment of size 2^{22}, we observe that the memory table is by far the longest. It contains approximately 14M rows, followed by th…
-
This page is accessible via [roadmap.vllm.ai](https://roadmap.vllm.ai)
### Themes.
As before, we categorized our roadmap into 6 broad themes: broad model support, wide hardware coverage, state of…
-
The Remote Persistent Memory Pool (RPMP) should work with latest master code, namely work with Spark3.1.1 and server as disaggregated shuffle media.
It's expected to be included in OAP 1.2 release.
-
Here is the development roadmap for 2024 Q4. Contributions and feedback are welcome ([**Join Bi-weekly Development Meeting**](https://t.co/4BFjCLnVHq)). Previous 2024 Q3 roadmap can be found in #634.
…
-
This is the continuation to the discussion #17999.
Background:
--------
In our group, we are working on developing an array distribution for the data residing on Fabric attached Memory, a disagg…
-
Congratulations on your paper being accepted by EuroSys 2025.! I am also studying distributed index based on disaggregated memory. I have read the paper and source code of Sherman before. Recently, I …
-
Hello Peter,
I have a question regarding remote swap trace. You mentioned that you implement a remote swap memory device and you use this swap memory to evaluate network requirement of resource dis…
-
## Motivation
The storage engine is the source of truth for a node. Raft and KV rely on the integrity of the storage engine's data, and breaches of its integrity can result in false query results, …