Merge pull request #141 from Anindyadeep/anindya/tinygrad-fix

TinyGrad Readme and small fixes.

bench_tinygrad/README.md

@@ -0,0 +1,34 @@
+# TinyGrad
+
+[![GitHub Repo](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/tinygrad/tinygrad)  
+
+TinyGrad is a minimalistic deep learning framework, very similar to [PyTorch](https://github.com/pytorch/pytorch). It's simplicity is inspired from the [micrograd](https://github.com/karpathy/micrograd) implementation by [Andrej Karpathy](https://karpathy.ai/). TinyGrad leverages different methods like lazy computation and kernel fusion techniques to run different operations. It supports various accelerators out of the box, including CPU, GPU etc. This benchmark implementation uses the [Llama 2 example](https://github.com/tinygrad/tinygrad/blob/master/examples/llama.py) written inside tinygrad/examples.
+
+
+### 🚀 Running the TinyGrad Benchmark.
+
+You can run the TinyGrad  benchmark using the following command:
+
+```bash
+./bench_tinygrad/bench.sh \
+  --prompt <value> \            # Enter a prompt string
+  --max_tokens <value> \        # Maximum number of tokens to output
+  --repetitions <value> \       # Number of repititions to be made for the prompt.
+  --log_file <file_path> \      # A .log file underwhich we want to write the results.
+  --device <cpu/cuda/metal> \   # The device in which we want to benchmark.
+  --models_dir <path_to_models> # The directory in which model weights are present
+```
+
+To get started quickly you can simply run:
+
+```bash
+./bench_tinygrad/bench.sh -d cuda
+```
+This will take all the default values (see in the [bench.sh](/bench_tinygrad/bench.sh) file) and perform the benchmarks. You can find all the benchmarks results for TinyGrad [here](/docs/llama2.md).
+
+
+### 👀 Some points to note:
+
+1. The current implementation of TinyGrad only supports Float16 for CUDA, CPU and Metal.
+2. This benchmark implementation expects the Raw Llama 2 weights from Meta AI to run LLama2 Model. So it assumes that you already accepted all the [terms and conditions](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) before running it.
+3. Please note, the current implementation won't work if tried to reproduce. There are certain conflicts with the main tinygrad repo. This will be fixed in the upcoming versions.

bench_tinygrad/bench.sh

@@ -2,30 +2,31 @@
 
 ########################################################################################################
 # Script: bench.sh
-# Description: This script runs benchmarks tinygrad llama benchmark.
+# Description: This script runs benchmarks TinyGrad llama benchmark.
 #
 # Usage: ./bench.sh [OPTIONS]
 # OPTIONS:
-#   -p, --prompt      Prompt for benchmarks (default: 'Explain what is a transformer')
-#   -r, --repetitions Number of repetitions for benchmarks (default: 2)
-#   -m, --max_tokens  Maximum number of tokens for benchmarks (default: 100)
-#   -d, --device      Device for benchmarks (possible values: 'metal', 'gpu', and 'cpu', default: 'cpu')
+#   -p, --prompt      Prompt for benchmarks (default: 'Write an essay about the transformer model architecture')
+#   -r, --repetitions Number of repetitions for benchmarks (default: 10)
+#   -m, --max_tokens  Maximum number of tokens for benchmarks (default: 512)
+#   -d, --device      Device for benchmarks (possible values: 'metal', 'cuda', and 'cpu', default: 'cuda')
 #   -lf, --log_file   Logging file name.
 #   -md, --models_dir Models directory.
 #   -h, --help        Show this help message
 ########################################################################################################
 
 set -euo pipefail
 
+CURRENT_DIR="$(pwd)"
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
 print_usage() {
     echo "Usage: $0 [OPTIONS]"
     echo "OPTIONS:"
-    echo "  -p, --prompt        Prompt for benchmarks (default: 'Explain what is a transformer')"
+    echo "  -p, --prompt        Prompt for benchmarks (default: 'Write an essay about the transformer model architecture')"
     echo "  -r, --repetitions   Number of repetitions for benchmarks (default: 10)"
-    echo "  -m, --max_tokens    Maximum number of tokens for benchmarks (default: 100)"
-    echo "  -d, --device        Device for benchmarks (possible values: 'metal', 'gpu', and 'cpu', default: 'cpu')"
+    echo "  -m, --max_tokens    Maximum number of tokens for benchmarks (default: 512)"
+    echo "  -d, --device        Device for benchmarks (possible values: 'metal', 'cuda', and 'cpu', default: 'cuda')"
     echo "  -lf, --log_file     Logging file name."
     echo "  -md, --models_dir   Models directory."
     echo "  -h, --help          Show this help message"
@@ -57,16 +58,29 @@ check_platform() {
 }
 
 check_python() {
-    if command -v python &> /dev/null
-    then
-        echo -e "\nUsing $(python --version)."
+    if command -v python &> /dev/null; then
+        PYTHON_CMD="python"
+    elif command -v python3 &> /dev/null; then
+        PYTHON_CMD="python3"
     else
-        echo -e "\nPython does not exist."
+        echo "Python is not installed."
         exit 1
     fi
 }
 
 setup() {
+
+    # Check if Logs folder exists else Make the logs folder
+    LOGS_FOLDER="$CURRENT_DIR/Logs"
+
+    if [ -d "$LOGS_FOLDER" ]; then
+        echo "Folder '$LOGS_FOLDER' already exists. Skipping."
+    else
+        # Create the folder
+        mkdir "$LOGS_FOLDER"
+        echo "'$LOGS_FOLDER' created."
+    fi
+
     echo -e "\nSetting up with $SCRIPT_DIR/setup.sh..."
     bash "$SCRIPT_DIR"/setup.sh "$1"
 }
@@ -86,7 +100,7 @@ run_llama_experiment() {
     declare -a tokens_per_second_array=()
 
     for ((i=1; i<=repetitions; i++)); do
-        tokens_per_second=$(python "$script_dir/tinygrad/examples/llama.py" \
+        tokens_per_second=$("$PYTHON_CMD" "$script_dir/tinygrad/examples/tiny.py" \
             --model "$models_dir/llama-2-7b-raw" \
             --prompt "$prompt" \
             --count "$max_tokens" \
@@ -179,15 +193,17 @@ while [ "$#" -gt 0 ]; do
             ;;
     esac
 done
-# Set default values if not provided
-PROMPT="${PROMPT:-"Explain what is a transformer"}"
-REPETITIONS="${REPETITIONS:-10}"
-MAX_TOKENS="${MAX_TOKENS:-100}"
-DEVICE="${DEVICE:-'cpu'}"
-LOG_FILENAME="${LOG_FILENAME:-"benchmark_$(date +'%Y%m%d%H%M%S').log"}"
-MODELS_DIR="${MODELS_DIR:-"./models"}"
 
 check_platform
 check_python
 setup "$DEVICE"
+
+# Set default values if not provided
+PROMPT="${PROMPT:-"Write an essay about the transformer model architecture"}"
+REPETITIONS="${REPETITIONS:-10}"
+MAX_TOKENS="${MAX_TOKENS:-512}"
+DEVICE="${DEVICE:-'cuda'}"
+LOG_FILENAME="${LOG_FILENAME:-"$LOGS_FOLDER/benchmark_pytorch_$(date +'%Y%m%d%H%M%S').log"}"
+MODELS_DIR="${MODELS_DIR:-"./models"}"
+
 run_benchmarks "$PROMPT" "$REPETITIONS" "$MAX_TOKENS" "$DEVICE" "$LOG_FILENAME" "$MODELS_DIR"

bench_tinygrad/setup.sh

@@ -12,8 +12,21 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 VENV_DIR="$SCRIPT_DIR/venv"
 
+check_python() {
+    if command -v python &> /dev/null; then
+        PYTHON_CMD="python"
+    elif command -v python3 &> /dev/null; then
+        PYTHON_CMD="python3"
+    else
+        echo "Python is not installed."
+        exit 1
+    fi
+}
+
+check_python
+
 if [ ! -d "$VENV_DIR" ]; then
-    python -m venv "$VENV_DIR"
+    "$PYTHON_CMD" -m venv "$VENV_DIR"
     echo "Virtual environment '$VENV_DIR' created."
     # shellcheck disable=SC1091
     source "$VENV_DIR/bin/activate"