tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

cont : fix comments

Browse Source
This commit is contained in:
Georgi Gerganov
2025-06-12 10:43:55 +03:00
parent b8b8d3f368
commit ed99a8ea04
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-context.cpp
View File

@ -941,7 +941,7 @@ int llama_context::decode(llama_batch & inp_batch) {
} }
} }
// this indicates we are doing pooled embedding, so we ignore batch.logits and output all tokens // this indicates we are doing pooled embedding
const bool embd_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE; const bool embd_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE;
int64_t n_outputs_all = 0; int64_t n_outputs_all = 0;
@ -2077,7 +2077,7 @@ void llama_context::opt_epoch_iter(
n_queued_tokens += n_tokens_all; n_queued_tokens += n_tokens_all;
// this indicates we are doing pooled embedding, so we ignore batch.logits and output all tokens // this indicates we are doing pooled embedding
const bool embd_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE; const bool embd_pooled = cparams.embeddings && cparams.pooling_type != LLAMA_POOLING_TYPE_NONE;
embd_seq.clear(); embd_seq.clear();