Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fulafel
7 days ago
|
parent
|
context
|
favorite
| on:
Flux 2 Klein pure C inference
Interesting that OpenBLAS and MPS are reportedly nearly the same speed although the README sounds like only MPS uses the GPU.
antirez
7 days ago
[–]
I think that this is because the current code does a terrible job at taking the activations in the GPU and fusing the kernels. This is the next thing to fix in this implementation indeed.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: