From 0c47e7953768296c9756b914661ebe2b88d2e2fe Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Mon, 2 Oct 2023 11:05:19 +0800
Subject: [PATCH] updated the API routing path and fixed a bug with threads

---
 gpttype_adapter.cpp | 6 +++++-
 koboldcpp.py        | 6 +++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/gpttype_adapter.cpp b/gpttype_adapter.cpp
index 39820712f..68db83448 100644
--- a/gpttype_adapter.cpp
+++ b/gpttype_adapter.cpp
@@ -788,6 +788,8 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
         llama_ctx_params.rope_freq_base = rope_freq_base;
         llama_ctx_params.rope_freq_scale = rope_freq_scale;
         llama_ctx_params.n_batch = blasbatchsize;
+        llama_ctx_params.n_threads = n_threads;
+        llama_ctx_params.n_threads_batch = n_blasthreads;
 
         #if defined(GGML_USE_CUBLAS)
         bool ts_all_zero = true;
@@ -1365,7 +1367,9 @@ generation_outputs gpttype_generate(const generation_inputs inputs, generation_o
         params.n_batch = bbs; //received reports of 1024 and above crashing on some models
         if(!ggml_cpu_has_gpublas())
         {
-            params.n_threads = 1; //do not limit here anymore.
+            //does not limit here for gguf anymore. this is kept for older models.
+            //new models will override threads inside decode fn.
+            params.n_threads = 1;
             params.n_threads_batch = 1;
         }
         else
diff --git a/koboldcpp.py b/koboldcpp.py
index 744359025..900be3c10 100755
--- a/koboldcpp.py
+++ b/koboldcpp.py
@@ -367,7 +367,7 @@ maxhordelen = 256
 modelbusy = threading.Lock()
 requestsinqueue = 0
 defaultport = 5001
-KcppVersion = "1.45.1"
+KcppVersion = "1.45.2"
 showdebug = True
 showsamplerwarning = True
 showmaxctxwarning = True
@@ -583,7 +583,7 @@ class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
                 pendtxtStr = ctypes.string_at(pendtxt).decode("UTF-8","ignore")
             response_body = (json.dumps({"results": [{"text": pendtxtStr}]}).encode())
 
-        elif self.path.endswith('/api/extra/oai/v1/models'):
+        elif self.path.endswith('/v1/models') or self.path.endswith('/models'):
             response_body = (json.dumps({"object":"list","data":[{"id":"koboldcpp","object":"model","created":1,"owned_by":"koboldcpp","permission":[],"root":"koboldcpp"}]}).encode())
 
         elif self.path.endswith(('/api')) or self.path.endswith(('/api/v1')):
@@ -684,7 +684,7 @@ class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
                 api_format = 2
                 kai_sse_stream_flag = True
 
-            if self.path.endswith('/api/extra/oai/v1/completions'):
+            if self.path.endswith('/v1/completions') or self.path.endswith('/completions'):
                 api_format = 3
 
             if api_format>0: