auto-round
a37363ca - feat: handle per-tensor FP8 dequantization for Devstral models (#1356)

Commit

26 days ago

feat: handle per-tensor FP8 dequantization for Devstral models (#1356) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author

SwekeR-463

Committer

lvliang-intel

Parents

8c41dcbf

auto-round a37363ca - feat: handle per-tensor FP8 dequantization for Devstral models (#1356)

auto-round
a37363ca - feat: handle per-tensor FP8 dequantization for Devstral models (#1356)