CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : fix n_outputs init

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-21 15:50:27 +02:00
parent f588a70da3
commit 3753b30d65
2 changed files with 5 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-context.h
View File

@@ -375,8 +375,8 @@ protected:
// populated only when pooling_type != LLAMA_POOLING_TYPE_NONE
std::map<llama_seq_id, std::vector<float>> embd_seq;
int32_t output_size = 0; // capacity (of tokens positions) for the output buffers
int32_t n_outputs = 0; // number of actually-used outputs in the current ubatch or last logical batch
int32_t n_outputs = 0; // number of actually-used outputs in the current ubatch or last logical batch
int32_t n_outputs_max = 0; // capacity (of tokens positions) for the output buffers
std::vector<int32_t> output_ids; // map batch token positions to ids of the logits and embd buffers