Logo
Explore Help
Register Sign In
biondizzle/vllm
1
0
Fork 0
You've already forked vllm
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

0 Releases 140 Tags

RSS Feed
  • v0.18.0rc2 89138b21cc
    Compare

    [Bugfix] Zero-init MLA attention output buffers to prevent NaN from CUDA graph padding (#37442)

    biondizzle released this 2026-03-19 01:44:16 +00:00

    Signed-off-by: Elvir Crncevic elvircrn@gmail.com
    Signed-off-by: Matthew Bonanni mbonanni@redhat.com
    Co-authored-by: Matthew Bonanni mbonanni@redhat.com
    (cherry picked from commit ef2c4f778d)

    Downloads
    • Source Code (ZIP)
    • Source Code (TAR.GZ)
Powered by Gitea Version: 1.25.2 Page: 189ms Template: 6ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API