CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : fix init of n_outputs (#12397)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-03-16 19:29:36 +02:00
committed by GitHub
parent 7b61bcc87c
commit dc079cfdff
1 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/llama-context.cpp
View File

@@ -285,11 +285,15 @@ llama_context::llama_context(
// reserve worst-case graph
if (!hparams.vocab_only) {
uint32_t n_seqs = 1; // TODO: worst-case number of sequences
uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);
const uint32_t n_seqs = 1; // TODO: worst-case number of sequences
const uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);
llama_token token = model.vocab.token_bos(); // not actually used by llama_build_graph, but required to choose between token and embedding inputs graph
// restore later
// TODO: something cleaner
const auto n_outputs_save = n_outputs;
// max number of outputs
n_outputs = n_tokens;
@@ -341,6 +345,8 @@ llama_context::llama_context(
}
}
n_outputs = n_outputs_save;
for (size_t i = 0; i < backend_ptrs.size(); ++i) {
ggml_backend_t backend = backend_ptrs[i];
ggml_backend_buffer_type_t buft = backend_buft[i];