Skip to content

GitLab

Commit fab00e26 authored by Tim Dettmers's avatar Tim Dettmers
Browse files

Version 0.41.2 + changelog.

parent ad6eef99
Show whitespace changes
Inline Side-by-side
Showing with 7 additions and 2 deletions
CHANGELOG.md
View file @ fab00e26
...@@ -311,7 +311,12 @@ User experience: ...@@ -311,7 +311,12 @@ User experience:
Performance: Performance:
- improved 4-bit inference performance for A100 GPUs. This degraded performance for A40/RTX3090 and RTX 4090 GPUs slightly. - improved 4-bit inference performance for A100 GPUs. This degraded performance for A40/RTX3090 and RTX 4090 GPUs slightly.
### 0.41.0 ### 0.41.1
Bug fixes: Bug fixes:
- Fixed bugs in dynamic exponent data type creation. Thank you @RossM, @KohakuBlueleaf, @ArrowM #659 #227 #262 #152 - Fixed bugs in dynamic exponent data type creation. Thank you @RossM, @KohakuBlueleaf, @ArrowM #659 #227 #262 #152
### 0.41.2
Feature:
- 4-bit serialization now supported. This enables 4-bit load/store. Thank you @poedator #753
setup.py
View file @ fab00e26
...@@ -18,7 +18,7 @@ def read(fname): ...@@ -18,7 +18,7 @@ def read(fname):
setup( setup(
name=f"bitsandbytes", name=f"bitsandbytes",
version=f"0.41.1", version=f"0.41.2",
author="Tim Dettmers", author="Tim Dettmers",
author_email="dettmers@cs.washington.edu", author_email="dettmers@cs.washington.edu",
description="k-bit optimizers and matrix multiplication routines.", description="k-bit optimizers and matrix multiplication routines.",
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment