Skip to content

I have used int32_t for llama_memory_seq_div#25892

Open
dogukandemirci-software-engineer wants to merge 1 commit into
ggml-org:masterfrom
dogukandemirci-software-engineer:fix/llama-h-int32
Open

I have used int32_t for llama_memory_seq_div#25892
dogukandemirci-software-engineer wants to merge 1 commit into
ggml-org:masterfrom
dogukandemirci-software-engineer:fix/llama-h-int32

Conversation

@dogukandemirci-software-engineer

Copy link
Copy Markdown

I have researched the llama.h and find a memory sequence divisorfunction to change type to guideline as guided in #4574 (for fixed width integer standart)

BEFORE
"""
LLAMA_API void llama_memory_seq_div(
llama_memory_t mem,
llama_seq_id seq_id,
llama_pos p0,
llama_pos p1,
int d);
"""

AFTER
"""
LLAMA_API void llama_memory_seq_div(
llama_memory_t mem,
llama_seq_id seq_id,
llama_pos p0,
llama_pos p1,
int32_t d);
"""

Closes #4574

…hile sibling params (p0, p1) are llama_pos (int32_t). Use int32_t for consistency with rest of the public API.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

llama : integer type consistency in llama.h

1 participant