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

llama : revert n_threads_batch logic

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-11-27 21:21:23 +02:00
parent e9b7a5cbd0
commit 87f4102a70
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@@ -5433,7 +5433,7 @@ static int llama_decode_internal(
GGML_ASSERT(n_tokens <= n_batch); GGML_ASSERT(n_tokens <= n_batch);
int n_threads = n_tokens < 32 ? cparams.n_threads : cparams.n_threads_batch; int n_threads = n_tokens == 1 ? cparams.n_threads : cparams.n_threads_batch;
GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT
const int64_t t_start_us = ggml_time_us(); const int64_t t_start_us = ggml_time_us();