From 09adfa70ada8fce2aeb799059620a208b1797d8a Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Wed, 22 May 2024 14:47:57 +0800
Subject: [PATCH] limit default threads to max 8 to deal with ecores

---
 README.md    | 2 +-
 koboldcpp.py | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index cc85b3ce9..ec2d1c436 100644
--- a/README.md
+++ b/README.md
@@ -58,7 +58,7 @@ when you can't use the precompiled binary directly, we provide an automated buil
   - For Arch Linux: Install `cblas` `openblas` and `clblast`.
   - For Debian: Install `libclblast-dev` and `libopenblas-dev`.
 - You can attempt a CuBLAS build with `LLAMA_CUBLAS=1`. You will need CUDA Toolkit installed. Some have also reported success with the CMake file, though that is more for windows.
-- For a full featured build (all backends), do `make LLAMA_OPENBLAS=1 LLAMA_CLBLAST=1 LLAMA_CUBLAS=1 LLAMA_VULKAN=1`
+- For a full featured build (all backends), do `make LLAMA_OPENBLAS=1 LLAMA_CLBLAST=1 LLAMA_CUBLAS=1 LLAMA_VULKAN=1`. (Note that `LLAMA_CUBLAS=1` will not work on windows, you need visual studio)
 - After all binaries are built, you can run the python script with the command `koboldcpp.py [ggml_model.bin] [port]`
 
 - Note: Many OSX users have found that the using Accelerate is actually faster than OpenBLAS. To try, you may wish to run with `--noblas` and compare speeds.
diff --git a/koboldcpp.py b/koboldcpp.py
index 24f939a23..18bd785da 100644
--- a/koboldcpp.py
+++ b/koboldcpp.py
@@ -3465,6 +3465,7 @@ if __name__ == '__main__':
     if os.cpu_count()!=None and os.cpu_count()>1:
         physical_core_limit = int(os.cpu_count()/2)
     default_threads = (physical_core_limit if physical_core_limit<=3 else max(3,physical_core_limit-1))
+    default_threads = (8 if default_threads > 8 else default_threads) #there is zero reason to exceed 8 threads by default. this helps avoid e-cores.
     parser.add_argument("--threads", metavar=('[threads]'), help="Use a custom number of threads if specified. Otherwise, uses an amount based on CPU cores", type=int, default=default_threads)
     compatgroup = parser.add_mutually_exclusive_group()
     compatgroup.add_argument("--usecublas", help="Use CuBLAS for GPU Acceleration. Requires CUDA. Select lowvram to not allocate VRAM scratch buffer. Enter a number afterwards to select and use 1 GPU. Leaving no number will use all GPUs. For hipBLAS binaries, please check YellowRoseCx rocm fork.", nargs='*',metavar=('[lowvram|normal] [main GPU ID] [mmq] [rowsplit]'), choices=['normal', 'lowvram', '0', '1', '2', '3', 'mmq', 'rowsplit'])