Update README.md and modify default value

msy-kato · May 28, 2024 · 86f042f · 86f042f
1 parent 834e4a8
commit 86f042f
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 5 deletions.
diff --git a/examples/batched-bench/README.md b/examples/batched-bench/README.md
@@ -13,13 +13,13 @@ There are 2 modes of operation:
 ./batched-bench MODEL_PATH [N_KV_MAX] [N_BATCH] [N_UBATCH] [FATTN] [IS_PP_SHARED] [NGL] [NT] [NTB] <PP> <TG> <PL>
 
 # LLaMA 7B, F16, N_KV_MAX = 16384 (8GB), prompt not shared
-./batched-bench ./models/llama-7b/ggml-model-f16.gguf 16384 2048 512 0 99
+./batched-bench ./models/llama-7b/ggml-model-f16.gguf 16384 2048 512 0 0 99
 
 # LLaMA 7B, Q8_0, N_KV_MAX = 16384 (8GB), prompt is shared
-./batched-bench ./models/llama-7b/ggml-model-q8_0.gguf 16384 2048 512 1 99
+./batched-bench ./models/llama-7b/ggml-model-q8_0.gguf 16384 2048 512 0 1 99
 
 # custom set of batches
-./batched-bench ./models/llama-7b/ggml-model-q8_0.gguf 2048 512 512 0 0 999 8 8 128,256,512 128,256 1,2,4,8,16,32
+./batched-bench ./models/llama-7b/ggml-model-q8_0.gguf 16384 2048 512 0 0 999 8 8 128,256,512 128,256 1,2,4,8,16,32
 ```
 
 ## Sample results

diff --git a/examples/batched-bench/batched-bench.cpp b/examples/batched-bench/batched-bench.cpp
@@ -34,11 +34,11 @@ int main(int argc, char ** argv) {
     if (argc == 1 || argv[1][0] == '-') {
         printf("usage: %s MODEL_PATH [N_KV_MAX] [N_BATCH] [N_UBATCH] [FATTN] [IS_PP_SHARED] [NGL] [NT] [NTB] <PP> <TG> <PL>\n", argv[0]);
         printf("  <PP>, <TG> and PL are comma-separated lists of numbers without spaces\n\n");
-        printf("  example: %s ggml-model-f16.gguf 2048 512 512 0 0 999 8 8 128,256,512 128,256 1,2,4,8,16,32\n\n", argv[0]);
+        printf("  example: %s ggml-model-f16.gguf 16384 2048 512 0 0 999 8 8 128,256,512 128,256 1,2,4,8,16,32\n\n", argv[0]);
         return 1 ;
     }
 
-    int n_kv_max        = 2048;
+    int n_kv_max        = 16384;
     int n_batch         = 2048;
     int n_ubatch        = 512;
     bool flash_attn     = false;