v1.5.0.post2

xorbitsai/inferencev1.5.0.post2Apr 21, 2025by qinxuye

AI Summary

Minor release including Docker build enhancements and UI bug fixes.

Key Highlights

Flash-attention support added to Dockerfile
Fixed UI cancellation function and Gemma-3-it max_tokens

Full Release Notes

# What's new in 1.5.0.post2 (2025-04-21)
These are the changes in xorbitsai/inference v1.5.0.post2.
## Enhancements
* BLD: support flash-attn at Dockerfile by @amumu96 in https://github.com/xorbitsai/inference/pull/3311
## Bug fixes
* BUG: [UI] fix the bug in the cancellation function. by @yiboyasss in https://github.com/xorbitsai/inference/pull/3301
* BUG: fix gemma-3-it max_tokens by @qinxuye in https://github.com/xorbitsai/inference/pull/3304
* BUG: fix potential progress error by @qinxuye in https://github.com/xorbitsai/inference/pull/3305

**Full Changelog**: https://github.com/xorbitsai/inference/compare/v1.5.0.post1...v1.5.0.post2