github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-09 15:08:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

llama 7B on 3090 benchmark (#3837)

Browse Source 
* llama 7B on 3090 benchmark

* symlink llama
This commit is contained in:
chenyu
2024-03-20 12:48:22 -04:00
committed by GitHub
parent 9452994201
commit 727de5ba1e
1 changed files with 13 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
.github/workflows/benchmark.yml vendored
View File

@@ -90,12 +90,22 @@ jobs:
uses: actions/checkout@v4
- name: Print nvidia-smi
run: nvidia-smi
- name: Symlink models and datasets
run: |
mkdir -p weights
ln -s ~/tinygrad/weights/LLaMA weights/LLaMA
- name: Run model inference benchmark
run: CUDA=1 python3 test/external/external_model_benchmark.py
- name: Test speed vs torch
run: CUDA=1 BIG=2 TORCHCUDA=1 python3 test/test_speed_v_torch.py | tee torch_speed.txt
- name: Run Tensor Core GEMM
run: CUDA=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt
- name: Run LLaMA
run: |
CUDA=1 JIT=0 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_unjitted.txt
CUDA=1 JIT=1 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_jitted.txt
- name: Run LLaMA with BEAM
run: CUDA=1 JIT=1 BEAM=2 CACHELEVEL=0 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_beam.txt
- name: Run GPT2
run: |
CUDA=1 JIT=0 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt
@@ -113,6 +123,9 @@ jobs:
onnx_inference_speed.csv
torch_speed.txt
matmul.txt
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt
gpt2_unjitted.txt
gpt2_jitted.txt
gpt2_half.txt