BREAKING
ZML Ships Free LLMD Inference Server
One Codebase, Many AI Chips
Broad Hardware Support
Major Vendors
●
NVIDIA CUDA
●
AMD ROCm
●
Google TPU
More Backends
●
AWS Trainium / Inferentia
●
Intel OneAPI
●
Apple Metal
0
people
0
M
raised ($)
0
stack launched
Free Preview, Not for Production
1
Pull Docker image
↓
2
Load from HF / S3 / GCS
↓
3
Preview only
Benchmarks Still To Come
AI NEWS BLITZ
French startup ZML has released a free server to run open LLMs across many AI chips.