Viewing profile — vans554
vans554
HN member- Joined
- Tue, Oct 17, 2017, 12:13 PM UTC
- HN karma
- 88
- Public activity
- 14 items
- HN profile
- View on Hacker News ↗
About vans554
No profile information was provided.
Recent public activity
-
comment
Comment #36793916
Pretty interesting. Using nightly + cu121 im getting 8.18 it/s, another 5% improvement vs 7.78 that cu118 gave.
-
comment
Comment #36787474
I accidentally stumbled upon this and did not expect such a speedup. It seems anything less than cu118 does not properly support the RTX4090 (or H100). Bumping to cuda12.2 with pyt…
- story
-
comment
Comment #34112715
I put Karlo diffusion by Kakao running as an inference endpoint on GPUX. Karlo Diffusion is more controllable, similar to Dalle-2. Make some images here https://explorer.gpux.ai/in…
- story
-
comment
Comment #34110781
Thanks.
-
comment
Comment #34067685
Yea but this is irrelevent unless you implying that FILM is better quality while nvfruc is lower quality but faster so applicable for realtime? if nvfruc is better quality + faster…
-
comment
Comment #34059786
very cool how does this compare to NVIDIA nvfruc? https://docs.nvidia.com/video-technologies/optical-flow-sdk/...
-
comment
Comment #34059453
People still go to traditional-school?
-
comment
Comment #34059402
Much needed thank you for doing gods work.
-
story
Show HN: GPUX, scalable inference for AI Models
I found that using models was too complex and it needed a simple interface (instead of documentation); while working on it, a few other companies created the same exact thing lol. …
-
comment
Comment #33745453
DDD is just microservices without head of line blocking not sure why everyone hates it. Instead of having 5 microservices you just build an umbrella app exposing the same 5 API. Ca…
-
comment
Comment #27347776
Mouse lag needs to be fixed.
-
comment
Comment #27267425
Would be cool to move realworld assets into virtual worlds, and vice versa.