Viewing profile — i386
i386
HN member- Joined
- Mon, Apr 20, 2009, 11:25 AM UTC
- HN karma
- 2,797
- Public activity
- 778 items
- HN profile
- View on Hacker News ↗
About i386
No profile information was provided.
Recent public activity
-
comment
Comment #49180877
Its an entire misunderstanding of how the layout system works.
-
comment
Comment #49138082
Most people working at the top of these large organizations don’t know how to make anything net new anymore. They pushed all the people that do out when padding their nests.
-
comment
Comment #48884710
exo is Mac only.
-
comment
Comment #48879661
I’d love a bug report - we can get it working for you!
-
comment
Comment #48879654
Our skippy library is a patch queue on top of llama that allows us to access internal information, such as activations, and filter tensors on model load.
-
comment
Comment #48877850
To be honest, both are very tough problems we don't have a good answer for yet. If that is something that concerns you, look into building a private mesh with trusted peers.
-
comment
Comment #48877841
Each stage has its own KV for the layers it hosts. You are on the money there, when one stage is waiting it's free for more parallelism. I am planning on exploiting this for more t…
-
comment
Comment #48877785
It can dynamically route. If a machine drops out of split, the topology is recalculated and the request is automatically retried.
-
comment
Comment #48877438
Thank you! AMD is a weak spot in our testing right now. If you’re willing to contribute or let us borrow some compute time, drop in on the Discord.
-
comment
Comment #48877390
The lab features two Mac Studios: an Apple M3 Ultra (32 CPU cores, 80 GPU cores, 256 GB unified memory) and an Apple M1 Ultra (20 CPU cores, 48 GPU cores, 128 GB unified memory), b…
-
comment
Comment #48877215
That isn’t true. llama RPC is incredibly slow but staged splits in skippy are orders of magnitude faster.
-
comment
Comment #48877199
This was done on my home lab simulating 5ms latency and jitter between machines. Splits work quite well if you your nodes are over WAN at metro latency’s but not super fast on glob…
-
comment
Comment #48877119
I’m one of the contributors to Mesh LLM and happy to answer any questions. I authored the skippy engine that allows you to split large models across nodes.
-
comment
Comment #47991852
PMs at Microsoft have incredibly bad taste
-
comment
Comment #47921191
I kinda fucking love it. He’s doing something. It’s interesting. There’s no scam. Let live!
-
comment
Comment #47622554
You can try this new model live using mesh-llm right now: https://www.anarchai.org/dashboard
-
comment
Comment #47614048
switch on version, then messageId…
-
comment
Comment #47614019
> I didn't know that Protobuf wasn't canonical but even without this knowledge, there are many other factors which make it an inferior format to JSON. If strict typing and versioni…
- story
-
comment
Comment #46995187
yeah this product does not exist
-
comment
Comment #46545229
I work for YouTube. You’re hired.
-
comment
Comment #46487010
At the WiseTech office in 2006 we had a small shrine in the corner dedicated to Tridge, the patron saint of hackers.
-
comment
Comment #45978194
This is very revisionist. While they have been catching up quickly there was no master 4D chess strategy here. Google was incredibly late to this game - Sergey had to come back fro…
-
comment
Comment #45575033
Android supremacy at its finest. I would never recommend a family member buying one. The history of this kind of thing is long and keeps continuing to happen.
-
comment
Comment #45112256
> What makes a group of coworkers into "an org"? Reporting lines that ladder up to a line in the P&L.