Viewing profile — conshama

conshama

HN member

No profile information was provided.

comment
Comment #48368289
Somehow I never got the hype around Groq. They served models with fast inference speed - that sounded great in theory - and as a user I was looking forward to use them. But, when I…

Tue, Jun 02, 2026, 10:23 AM UTC
comment
Comment #48223402
[dead]

Thu, May 21, 2026, 2:37 PM UTC
comment
Comment #41727768
Yes.

Thu, Oct 03, 2024, 6:09 AM UTC
comment
Comment #41723714
related: https://www.nonbios.ai/post/deploying-large-405b-models-in-f... tldr: uses the latest rocm 6.2 to run full precision inference for llama 405b on a single node 8 x MI300x A…

Wed, Oct 02, 2024, 6:35 PM UTC
comment
Comment #41723680
Wed, Oct 02, 2024, 6:31 PM UTC
comment
Comment #41712581
Seems to me that the only difference between Anthropic and OpenAI is that Anthropic was for-profit from day one and OpenAI is from day yesterday. I pay for both, and pretty sure th…

Tue, Oct 01, 2024, 6:50 PM UTC