model : more uniform output id handling (#14275)

Browse Source

* model : more uniform output id handling

ggml-ci

* cont : revert n_outputs < n_tokens optimization

ggml-ci

* cont : fix out_ids initialization

ggml-ci

...

This commit is contained in:

Georgi Gerganov

2025-06-20 10:50:27 +03:00

committed by GitHub

parent 4c9fdfbe15

commit 812939a9e9

2 changed files with 459 additions and 442 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

847

src/llama-model.cpp

File diff suppressed because it is too large Load Diff