tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 20:58:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : rework embeddings logic (#14208)

Browse Source 
* llama : rework embeddings logic

ggml-ci

* cont : fix rerank

ggml-ci

* cont : engrish [no ci]

* cont : fix rerank

ggml-ci

* server : support both embeddings and completions with single model

ggml-ci

* cont : avoid embeddings_org

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-16 14:14:00 +03:00
committed by GitHub
parent 3ba0d843c6
commit d3e64b9f49
16 changed files with 159 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-memory.h
View File

@ -73,7 +73,7 @@ struct llama_memory_i {
virtual llama_memory_state_ptr init_batch(
const llama_batch & batch,
uint32_t n_ubatch,
bool embd_pooled) = 0;
bool embd_all) = 0;
// simulate full cache, used for allocating worst-case compute buffers
virtual llama_memory_state_ptr init_full() = 0;