llama : have n_batch default to 512 (#1091)

* set default n_batch to 512 when using BLAS

* spacing

* alternate implementation of setting different n_batch for BLAS

* set n_batch to 512 for all cases

diff --git a/examples/common.h b/examples/common.h
index cbbc2dfab16de11969f67e0fcfd8cd15b7f5e62b..0470368d58acbc0004478f3cd5132dabd4590204 100644 (file)
--- a/examples/common.h
+++ b/examples/common.h
@@ -20,7 +20,7 @@ struct gpt_params {
     int32_t repeat_last_n = 64;   // last n tokens to penalize
     int32_t n_parts       = -1;   // amount of model parts (-1 = determine from model dimensions)
     int32_t n_ctx         = 512;  // context size
-    int32_t n_batch       = 8;    // batch size for prompt processing
+    int32_t n_batch       = 512;  // batch size for prompt processing (must be >=32 to use BLAS)
     int32_t n_keep        = 0;    // number of tokens to keep from initial prompt
 
     // sampling parameters