CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

cont : add TODO

Browse Source
This commit is contained in:
Georgi Gerganov
2025-07-24 16:31:10 +03:00
parent 5e58711c28
commit 978c88ba0a
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/llama.h
View File

@@ -956,6 +956,7 @@ extern "C" {
// in the order they have appeared in the batch. // in the order they have appeared in the batch.
// Rows: number of tokens for which llama_batch.logits[i] != 0 // Rows: number of tokens for which llama_batch.logits[i] != 0
// Cols: n_vocab // Cols: n_vocab
// TODO: deprecate in favor of llama_get_logits_ith() (ref: https://github.com/ggml-org/llama.cpp/pull/14853#issuecomment-3113143522)
LLAMA_API float * llama_get_logits(struct llama_context * ctx); LLAMA_API float * llama_get_logits(struct llama_context * ctx);
// Logits for the ith token. For positive indices, Equivalent to: // Logits for the ith token. For positive indices, Equivalent to:
@@ -970,6 +971,7 @@ extern "C" {
// in the order they have appeared in the batch. // in the order they have appeared in the batch.
// shape: [n_outputs*n_embd] // shape: [n_outputs*n_embd]
// Otherwise, returns NULL. // Otherwise, returns NULL.
// TODO: deprecate in favor of llama_get_embeddings_ith() (ref: https://github.com/ggml-org/llama.cpp/pull/14853#issuecomment-3113143522)
LLAMA_API float * llama_get_embeddings(struct llama_context * ctx); LLAMA_API float * llama_get_embeddings(struct llama_context * ctx);
// Get the embeddings for the ith token. For positive indices, Equivalent to: // Get the embeddings for the ith token. For positive indices, Equivalent to: