Github is not acting normal...
Our LMCache logo suddenly disappeared today, we didn't make any change. And we cannot even clone the repo using ssh.
Github bad bad.
210
Happy to meet with @EmbeddedLLM people in person! Thanks for all the hardware supports in @vllm_project and @lmcache !
vLLM team @vllm_project , reunited at Ray Summit! (Lowkey: can't wait to meet our magic @KaichaoYou and @darklight1337 in person!)
Can't wait to meet our magic @KaichaoYou and @darklight1337 in person!
Ray summit 2025 takeaways:
1. Ray is now in PyTorch Foundation
2. Ray supports RDMA (finally)
3. Anyscale runtime, basically Ray + better perf and fault tolerance/observability etc.
4. Anyscale is building multi-resource cloud, and collaborating with Azure.
#raysummit2025 #vllm
1
164
💰Want CHEAP GPU cloud?
💡Wanna store ALL your users’ history&docs as KV cache to save cost—but can’t get open source to run?
Try TensorMesh SaaS:
⚡️$3.09/hr H100
😄No vendor lock-in
🧠Any open-source model
🪄OpenAI-API compatible
Join the waitlist🚀: tensormesh.ai/beta-waitlist
LMCache in Redis Release event!
Plus random creation by Kobe from @lmcache
OMG a movie created by AI is so good and so like black mirror! Can't help watching it again and again
youtube.com/watch?v=gx8rMzlG…
1
97
20% or more acceptance rate for OSDI means --- 15% more papers being accepted 😍
Guys we should 100% submit to OSDI this year.
1
2
145
🤯 Believe it or not, even when an LLM generates just ONE SINGLE word, it can still be powerful!
Say in recommendation: all it takes is to answer “Should we recommend post X to user Y?” with Yes or No. That’s it!💪
Our paper optimizes this workload in vLLM and got into SoSP🚀














