b11387: spec : fix n-gram drafts rejected at temp > 0 after truncation (#29924)
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
Co-authored-by: Pranesh Gonegandla pgonegandla@nvidia.com
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
Co-authored-by: Pranesh Gonegandla pgonegandla@nvidia.com
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.