move sync script back in for now

llama/README.md

@@ -12,7 +12,6 @@ Supported:
 - [x] Linux CUDA
 - [x] Linux ROCm
 - [x] Llava
-- [x] Parallel Requests
 
 Extra build steps are required for CUDA and ROCm on Windows since `nvcc` and `hipcc` both require using msvc as the host compiler. For these small dlls are created:
 
@@ -61,6 +60,8 @@ go build -tags=cuda .
 
 ## Windows
 
+Download [w64devkit](https://github.com/skeeto/w64devkit/releases/latest) for a simple MinGW development environment.
+
 ### CUDA
 
 Install the [CUDA toolkit v11.3.1](https://developer.nvidia.com/cuda-11-3-1-download-archive) then build the cuda code:
@@ -95,9 +96,8 @@ go build -tags=rocm .
 
 ## Syncing with llama.cpp
 
-To update this package to the latest llama.cpp code, use the `scripts/sync_llama.sh` script from the root of this repo:
+To update this package to the latest llama.cpp code, use the `sync_llama.sh` script from the root of this repo:
 
 ```
-cd ollama
-./scripts/sync_llama.sh ../llama.cpp
+./sync_llama.sh ../../llama.cpp
 ```

llama/runner/README.md

@@ -1,11 +1,15 @@
 # `runner`
 
-A subprocess runner for loading a model and running inference via a small http web server.
+A minimial runner for loading a model and running inference via a http web server.
 
 ```
 ./runner -model <model binary>
 ```
 
+### Completion
+
 ```
-curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/
+curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/completion
 ```
+
+### Embeddings

scripts/sync_llama.sh → llama/sync_llama.sh

@@ -11,7 +11,7 @@ if [ -z "$src_dir" ]; then
 fi
 
 # Set the destination directory
-dst_dir=./llama
+dst_dir=.
 
 # llama.cpp
 cp $src_dir/unicode.cpp $dst_dir/unicode.cpp
@@ -106,7 +106,7 @@ for IN in $dst_dir/*.{c,h,cpp,m,metal,cu}; do
 done
 
 # ggml-metal
-sed -e '/#include "ggml-common.h"/r llama/ggml-common.h' -e '/#include "ggml-common.h"/d' < $dst_dir/ggml-metal.metal > temp.metal
+sed -e '/#include "ggml-common.h"/r ggml-common.h' -e '/#include "ggml-common.h"/d' < $dst_dir/ggml-metal.metal > temp.metal
 TEMP_ASSEMBLY=$(mktemp)
 echo ".section __DATA, __ggml_metallib"   >  $TEMP_ASSEMBLY
 echo ".globl _ggml_metallib_start"        >> $TEMP_ASSEMBLY