Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
bitsandbytes
Commits
d4755335
Commit
d4755335
authored
May 21, 2025
by
Matthew Douglas
Browse files
Update README.md
parent
70bacda7
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
28 additions
and
24 deletions
+28
-24
README.md
README.md
+28
-24
No files found.
README.md
View file @
d4755335
...
...
@@ -36,44 +36,45 @@ bitsandbytes has the following minimum requirements for all platforms:
</thead>
<tbody>
<tr>
<td
colspan=
"4"
>
🐧
<strong>
Linux
</strong></td>
<td
colspan=
"4"
>
🐧
<strong>
Linux
, glibc >= 2.24
</strong></td>
</tr>
<tr>
<td
align=
"right"
>
x86-64
</td>
<td>
◻️ CPU
</td>
<td></td>
<td>
AVX2
</td>
<td>
〰️ Partial Support
</td>
</tr>
<tr>
<td></td>
<td>
🟩 NVIDIA GPU
</td>
<td>
🟩 NVIDIA GPU
<br><code>
cuda
</code>
</td>
<td>
SM50+ minimum
<br>
SM75+ recommended
</td>
<td>
✅ Full Support
*
</td>
<td>
✅ Full Support
</td>
</tr>
<tr>
<td></td>
<td>
🟥 AMD GPU
</td>
<td>
gfx90a, gfx942, gfx1100
</td>
<td>
🟥 AMD GPU
<br><code>
cuda
</code></td>
<td>
CDNA: gfx90a, gfx942
<br>
RDNA: gfx1100, gfx1200
</td>
<td>
🚧 In Development
</td>
</tr>
<tr>
<td></td>
<td>
🟦 Intel
X
PU
</td>
<td>
🟦 Intel
G
PU
<br><code>
xpu
</code>
</td>
<td>
Data Center GPU Max Series
(Ponte Vecchio)
<br>
Arc A-Series (Alchemist)
<br>
Data Center GPU Max Series
<br>
Arc A-Series (Alchemist)
<br>
Arc B-Series (Battlemage)
</td>
<td>
🚧 In Development
</td>
</tr>
<!--
<tr>
<td></td>
<td>
🟦
Intel
HPU
</td>
<td>
🟪
Intel
Gaudi
<br><code>
hpu
</code>
</td>
<td>
Gaudi1, Gaudi2, Gaudi3
</td>
<td>
🚧
</td>
<td>
🚧
In Development
</td>
</tr>
--->
<tr>
<td
align=
"right"
>
aarch64
</td>
<td>
◻️ CPU
</td>
...
...
@@ -82,12 +83,12 @@ bitsandbytes has the following minimum requirements for all platforms:
</tr>
<tr>
<td></td>
<td>
🟩 NVIDIA GPU
</td>
<td>
🟩 NVIDIA GPU
<br><code>
cuda
</code>
</td>
<td>
SM75, SM80, SM90, SM100
</td>
<td>
✅ Full Support
*
</td>
<td>
✅ Full Support
</td>
</tr>
<tr>
<td
colspan=
"4"
>
🪟
<strong>
Windows
</strong></td>
<td
colspan=
"4"
>
🪟
<strong>
Windows
11 / Windows Server 2019+
</strong></td>
</tr>
<tr>
<td
align=
"right"
>
x86-64
</td>
...
...
@@ -97,13 +98,13 @@ bitsandbytes has the following minimum requirements for all platforms:
</tr>
<tr>
<td></td>
<td>
🟩 NVIDIA GPU
</td>
<td>
🟩 NVIDIA GPU
<br><code>
cuda
</code>
</td>
<td>
SM50+ minimum
<br>
SM75+ recommended
</td>
<td>
✅ Full Support
*
</td>
<td>
✅ Full Support
</td>
</tr>
<tr>
<td></td>
<td>
🟦 Intel
X
PU
</td>
<td>
🟦 Intel
G
PU
<br><code>
xpu
</code>
</td>
<td>
Arc A-Series (Alchemist)
<br>
Arc B-Series (Battlemage)
...
...
@@ -111,19 +112,22 @@ bitsandbytes has the following minimum requirements for all platforms:
<td>
🚧 In Development
</td>
</tr>
<tr>
<td
colspan=
"4"
>
🍎
<strong>
macOS
</strong></td>
<td
colspan=
"4"
>
🍎
<strong>
macOS
13.1+
</strong></td>
</tr>
<tr>
<td
align=
"right"
>
arm64
</td>
<td>
◻️ CPU
/ Metal
</td>
<td>
◻️ CPU
</td>
<td>
Apple M1+
</td>
<td>
❌ Under consideration
</td>
<td>
🛣️ Future Roadmap
</td>
</tr>
<tr>
<td></td>
<td>
⬜ Metal
<br><code>
mps
</code></td>
<td>
Apple M1+
</td>
<td>
🛣️ Future Roadmap
</td>
</tbody>
</table>
\*
Accelerated INT8 requires SM75+.
## :book: Documentation
*
[
Official Documentation
](
https://huggingface.co/docs/bitsandbytes/main
)
*
🤗
[
Transformers
](
https://huggingface.co/docs/transformers/quantization/bitsandbytes
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment