From 0480362f12298c7e62db3137144a1de720f2a8b3 Mon Sep 17 00:00:00 2001
From: netrunnereve <139727413+netrunnereve@users.noreply.github.com>
Date: Sun, 6 Aug 2023 00:44:29 -0400
Subject: [PATCH] remove from llama_context_params

---
 examples/common.cpp | 1 -
 llama.cpp           | 1 -
 llama.h             | 1 -
 3 files changed, 3 deletions(-)

diff --git a/examples/common.cpp b/examples/common.cpp
index 031868d90..46ceef966 100644
--- a/examples/common.cpp
+++ b/examples/common.cpp
@@ -668,7 +668,6 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
     lparams.embedding       = params.embedding;
     lparams.rope_freq_base  = params.rope_freq_base;
     lparams.rope_freq_scale = params.rope_freq_scale;
-    lparams.pp_threads      = params.pp_threads;
 
     return lparams;
 }
diff --git a/llama.cpp b/llama.cpp
index 97c5e0cb0..01c904a34 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -895,7 +895,6 @@ struct llama_context_params llama_context_default_params() {
         /*.rms_norm_eps                =*/ LLAMA_DEFAULT_RMS_EPS,
         /*.gpu_layers                  =*/ 0,
         /*.main_gpu                    =*/ 0,
-        /*.pp_threads                  =*/ GGML_DEFAULT_N_THREADS,
         /*.tensor_split                =*/ nullptr,
         /*.rope_freq_base              =*/ 10000.0f,
         /*.rope_freq_scale             =*/ 1.0f,
diff --git a/llama.h b/llama.h
index 0bbdd6759..c57e84654 100644
--- a/llama.h
+++ b/llama.h
@@ -94,7 +94,6 @@ extern "C" {
         float    rms_norm_eps; // rms norm epsilon (TEMP - will be moved to model hparams)
         int32_t  n_gpu_layers; // number of layers to store in VRAM
         int32_t  main_gpu;     // the GPU that is used for scratch and small tensors
-        int32_t  pp_threads;   // number of threads used for prompt processing only
 
         const float * tensor_split; // how to split layers across multiple GPUs (size: LLAMA_MAX_DEVICES)