Commit 2cce9fd
authored
llama : refactor sampling_info to use buffer_view template (ggml-org#19368)
* llama : refactor sampling_info to use buffer_view template
This commit updates the sampling_info struct in llama-context to use a
buffer_view template for the logits, probs, sampled tokens, and
candidates buffers.
The motivation for this is to simplify the code, improve type safety
and readability.1 parent 612db61 commit 2cce9fd
3 files changed
Lines changed: 107 additions & 115 deletions
0 commit comments