/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
Microsoft BitNet: inference framework for 1-bit LLMs
(github.com)
167 points
galeos
| 1 comments |
18 Oct 24 09:10 UTC
|
HN request time: 0.223s
|
source
1.
Scene_Cast2
◴[
18 Oct 24 16:26 UTC
]
No.
41880929
[source]
▶
>>41877609 (OP)
#
Neat. Would anyone know where the SDPA kernel equivalent is? I poked around the repo, but only saw some form of quantization code with vectorized intrinsics.
ID:
GO
↑