@Wbackdown I would expect not as fast as a trade off, larger but possible vs smaller faster (such is life).
0
0
1
9
New Mesh plugins for Apple Silicon:
⚡ Uzu: high-throughput Metal inference for Qwen 3.8 & more
🧠 DwarfStar: run huge DeepSeek V4 models locally
💾 Slotstream: SSD-backed MoE for Macs with less RAM
github.com/Mesh-LLM/uzu-r…
github.com/Mesh-LLM/ds4-p…
github.com/Mesh-LLM/slots…
⚡ Uzu: high-throughput Metal inference for Qwen 3.8 & more
🧠 DwarfStar: run huge DeepSeek V4 models locally
💾 Slotstream: SSD-backed MoE for Macs with less RAM
github.com/Mesh-LLM/uzu-r…
github.com/Mesh-LLM/ds4-p…
github.com/Mesh-LLM/slots…
1
0
0
5
Mesh LLM retweeted
this was fun to build
- fork of signal
- agent built with GDK
- using open weights model
- served via e2ee mesh-llm
- via private GPU TEE
- making private search tool calls
- paid for with ₿ over LN
a cool stack of permissionless & open source tech all working together!
- fork of signal
- agent built with GDK
- using open weights model
- served via e2ee mesh-llm
- via private GPU TEE
- making private search tool calls
- paid for with ₿ over LN
a cool stack of permissionless & open source tech all working together!
An agent inside Signal using decentralized compute paid for with bitcoin
@moneyball demos a fork of Signal built by @matbalez using @Mesh_LLM and @lexeapp ↓
Timestamps:
0:00 - Demo: agent inside Signal
10:51 - The economics of decentralized compute
14:39 - Running inference at home
13
24
150
153,702
Mesh LLM retweeted
Right on - this is what we made MeshLLM for (well that and some procrastination: github.com/mesh-llm/mesh-…
Metal, CPU, CUDA (various), ROCm, Vulkan, x86_64, arm, windows/mac/linux and appropriate combinations.
(fingers are sore).
Metal, CPU, CUDA (various), ROCm, Vulkan, x86_64, arm, windows/mac/linux and appropriate combinations.
(fingers are sore).
this is THE time to be revisiting distributed inference on heterogeneous hardware, software is collapsing the barriers of hardware incompatibility
0
2
1
47
we have shifted a fair bit of dev to buzz to try out multi player agents, just to see how it goes. Some findings from the other month: engineering.block.xyz/blog/shifting-…
0
0
1
34
Right on - this is what we made MeshLLM for (well that and some procrastination: github.com/mesh-llm/mesh-…
Metal, CPU, CUDA (various), ROCm, Vulkan, x86_64, arm, windows/mac/linux and appropriate combinations.
(fingers are sore).
Metal, CPU, CUDA (various), ROCm, Vulkan, x86_64, arm, windows/mac/linux and appropriate combinations.
(fingers are sore).
this is THE time to be revisiting distributed inference on heterogeneous hardware, software is collapsing the barriers of hardware incompatibility
0
2
1
47