mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-28 18:05:57 +01:00
657b8a77bd
This commit addresses an inconsistency during inference by adding a new member to the `templates_params` struct to indicate whether the chat is in inference mode. This allows the gpt-oss specific function `common_chat_params_init_gpt_oss` to check this flag and the `add_generation_prompt` flag to determine if it should replace the `<|return|>` token with the `<|end|>` token in the prompt. The motivation for this change is to ensure that the formatted prompt of past messages in `common_chat_format_single` matches the output of the formatted new message. The issue is that the gpt-oss template returns different end tags: `<|return|>` when `add_generation_prompt` is false, and `<|end|>` when `add_generation_prompt` is true. This causes the substring function to start at an incorrect position, resulting in tokenization starting with 'tart|>' instead of '<|start|>'. Resolves: https://github.com/ggml-org/llama.cpp/issues/15417 |
||
|---|---|---|
| .. | ||
| arg.cpp | ||
| arg.h | ||
| base64.hpp | ||
| build-info.cpp.in | ||
| chat-parser.cpp | ||
| chat-parser.h | ||
| chat.cpp | ||
| chat.h | ||
| CMakeLists.txt | ||
| common.cpp | ||
| common.h | ||
| console.cpp | ||
| console.h | ||
| json-partial.cpp | ||
| json-partial.h | ||
| json-schema-to-grammar.cpp | ||
| json-schema-to-grammar.h | ||
| llguidance.cpp | ||
| log.cpp | ||
| log.h | ||
| ngram-cache.cpp | ||
| ngram-cache.h | ||
| regex-partial.cpp | ||
| regex-partial.h | ||
| sampling.cpp | ||
| sampling.h | ||
| speculative.cpp | ||
| speculative.h | ||