We welcome LightSeek Foundation @lightseekorg as a Silver Member of PyTorch Foundation.
Its membership deepens LightSeek Foundation’s commitment to building open inference infrastructure with the community. LightSeek Foundation’s TokenSpeed and SMG are PyTorch Ecosystem projects.
Read the announcement: pytorch.org/blog/pytorch-f…
Its membership deepens LightSeek Foundation’s commitment to building open inference infrastructure with the community. LightSeek Foundation’s TokenSpeed and SMG are PyTorch Ecosystem projects.
Read the announcement: pytorch.org/blog/pytorch-f…
LightSeek Foundation has joined the @PyTorch Foundation as a Silver Member.
TokenSpeed and SMG are both PyTorch Ecosystem projects. This membership deepens our commitment to building open inference infrastructure with the community.
As our president @zhyncs42 shared: “Efficient to making AI accessible at global scale, and we believe the infrastructure behind it must be open.”
We look forward to working with the PyTorch community to improve performance, lower costs, and make AI more accessible.
Read the announcement: pytorch.org/blog/pytorch-f…
Oct 21, 2026 · 10:57 PM UTC
4
3
40
7,811
@PyTorch @lightseekorg Bringing `TokenSpeed` and `SMG` directly into the PyTorch Ecosystem is a big win for open LLM serving!
As inference shifts toward prefill-decode disaggregation and KV-cache-aware routing at the gateway layer, how tightly will SMG integrate with native `torch.compile`?
As inference shifts toward prefill-decode disaggregation and KV-cache-aware routing at the gateway layer, how tightly will SMG integrate with native `torch.compile`?
0
0
0
104
@PyTorch @lightseekorg open inference matters more to small teams than anyone else. we can't afford the closed stuff
1
0
1
36
@PyTorch @lightseekorg nice to see open inference infrastructure taking shape, hope it benefits many 🤖
0
0
0
18