Skip to content

docs(changelog): note the CUDA pull-variant fix #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
prabod wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −0
Open

docs(changelog): note the CUDA pull-variant fix #39

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,10 @@ overhaul of `basert serve`.

### Fixed

- **CUDA model resolution.** `basert pull`/`chat <id>` on NVIDIA GB10 now fetches
the CUDA-native bundle instead of the universal one it couldn't load
(`no function named 'gemv_q4'`). The 0.2.0 Linux/arm64 CUDA download was updated
in place with this fix.
- **Chunked-decode correctness on CUDA.** Free generation past the decode chunk size
no longer repeats an earlier block (an eager-dispatch write-after-read hazard);
prefill and teacher-forced decode were always correct.
Expand Down
Loading