Don't tell users to use a bad number of threads

.devops/tools.sh

@@ -34,7 +34,7 @@ else
     echo "Unknown command: $arg1"
     echo "Available commands: "
     echo "  --run (-r): Run a model previously converted into ggml"
-    echo "              ex: -m /models/7B/ggml-model-q4_0.bin -p \"Building a website can be done in 10 simple steps:\" -t 8 -n 512"
+    echo "              ex: -m /models/7B/ggml-model-q4_0.bin -p \"Building a website can be done in 10 simple steps:\" -n 512"
     echo "  --convert (-c): Convert a llama model into ggml"
     echo "              ex: \"/models/7B/\" 1"
     echo "  --quantize (-q): Optimize with quantization process ggml"

README.md

@@ -39,7 +39,7 @@ Supported platforms:
 Here is a typical run using LLaMA-7B:
 
 ```java
-make -j && ./main -m ./models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -t 8 -n 512
+make -j && ./main -m ./models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
 I llama.cpp build info:
 I UNAME_S:  Darwin
 I UNAME_P:  arm
@@ -150,7 +150,7 @@ python3 convert-pth-to-ggml.py models/7B/ 1
 ./quantize.sh 7B
 
 # run the inference
-./main -m ./models/7B/ggml-model-q4_0.bin -t 8 -n 128
+./main -m ./models/7B/ggml-model-q4_0.bin -n 128
 ```
 
 When running the larger models, make sure you have enough disk space to store all the intermediate files.
@@ -164,7 +164,7 @@ In this mode, you can always interrupt generation by pressing Ctrl+C and enter o
 
 Here is an example few-shot interaction, invoked with the command
 ```
-./main -m ./models/13B/ggml-model-q4_0.bin -t 8 -n 256 --repeat_penalty 1.0 --color -i -r "User:" \
+./main -m ./models/13B/ggml-model-q4_0.bin -n 256 --repeat_penalty 1.0 --color -i -r "User:" \
                                            -p \
 "Transcript of a dialog, where the User interacts with an Assistant named Bob. Bob is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.
 
@@ -218,13 +218,13 @@ docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full --all-in-on
 On complete, you are ready to play!
 
 ```bash
-docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full --run -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -t 8 -n 512
+docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full --run -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
 ```
 
 or with light image:
 
 ```bash
-docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:light -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -t 8 -n 512
+docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:light -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
 ```
 
 ## Limitations

ggml.c

@@ -9318,10 +9318,6 @@ static thread_ret_t ggml_graph_compute_thread(void * data) {
 }
 
 void ggml_graph_compute(struct ggml_context * ctx, struct ggml_cgraph * cgraph) {
-    if (cgraph->n_threads <= 0) {
-        cgraph->n_threads = 8;
-    }
-
     const int n_threads = cgraph->n_threads;
 
     struct ggml_compute_state_shared state_shared = {

utils.cpp

@@ -16,6 +16,18 @@
  #endif
 
 bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
+    // determine sensible default number of threads.
+    // std::thread::hardware_concurrency may not be equal to the number of cores, or may return 0.
+#ifdef __linux__
+    std::ifstream cpuinfo("/proc/cpuinfo");
+    params.n_threads = std::count(std::istream_iterator<std::string>(cpuinfo),
+                                  std::istream_iterator<std::string>(),
+                                  std::string("processor"));
+#endif
+    if (params.n_threads == 0) {
+        params.n_threads = std::max(1, (int32_t) std::thread::hardware_concurrency());
+    }
+
     for (int i = 1; i < argc; i++) {
         std::string arg = argv[i];
 

utils.h

@@ -14,7 +14,7 @@
 
 struct gpt_params {
     int32_t seed      = -1; // RNG seed
-    int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
+    int32_t n_threads;
     int32_t n_predict = 128; // new tokens to predict
     int32_t repeat_last_n = 64;  // last n tokens to penalize
     int32_t n_ctx = 512; //context size