Skip to content

Commit

Permalink
Merge pull request #46 from coreweave/eta/serialization-optimization
Browse files Browse the repository at this point in the history
perf(serialization): Optimize bulk serialization through concurrency
  • Loading branch information
wbrown authored Sep 9, 2023
2 parents 36910dc + a339d0c commit 1018750
Show file tree
Hide file tree
Showing 4 changed files with 666 additions and 299 deletions.
7 changes: 6 additions & 1 deletion CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

### Changed

- `TensorSerializer.write_module` has been optimized further for a speedup of
~3.6x on CUDA modules and ~3.1x faster on CPU modules

### Fixed

- `CURLStreamFile.response_headers` no longer has a chance to have incomplete
- `CURLStreamFile.response_headers` no longer has a chance to contain incomplete
header information

## [2.3.0] - 2023-09-06
Expand Down
2 changes: 1 addition & 1 deletion tensorizer/_version.py
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "2.3.1.dev0"
__version__ = "2.3.1.dev1"
Loading

0 comments on commit 1018750

Please sign in to comment.