tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-07 17:24:18 -04:00
Code Issues Packages Projects Releases Wiki Activity

refactor: rename *_is_hybrid -> *_is_hybrid_recurrent

Browse Source 
The implementation of the hybrid cache intentionally does not specify the
types of the child caches, so there was a naming mismatch with these
predicate functions that used "hybrid" to imply "hybrid recurrent."

Branch: HybridCache

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
2025-05-28 06:48:53 -06:00
parent fc9e0b576e
commit fb26e95ae7
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/llama.h
View File

@@ -573,7 +573,7 @@ extern "C" {
LLAMA_API bool llama_model_is_recurrent(const struct llama_model * model);
// Returns true if the model is hybrid-recurrent (like Jamba, Bamba, etc.)
LLAMA_API bool llama_model_is_hybrid(const struct llama_model * model);
LLAMA_API bool llama_model_is_hybrid_recurrent(const struct llama_model * model);
// Returns 0 on success
LLAMA_API uint32_t llama_model_quantize(