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 6 gpus benchmark (#3773)

Browse Source
This commit is contained in:
chenyu
2024-03-16 11:38:52 -04:00
committed by GitHub
parent 07324b56d5
commit 77febb44e6
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
.github/workflows/benchmark.yml vendored
View File

@@ -153,12 +153,14 @@ jobs:
run: HSA=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt
- name: Run Stable Diffusion
run: HSA=1 python3 examples/stable_diffusion.py --seed 0 --noshow --timing | tee sd.txt
- name: Run LLaMA
- name: Run LLaMA 7B
run: |
HSA=1 JIT=0 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_unjitted.txt
HSA=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
- name: Run LLaMA 7B with BEAM
run: HSA=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 LLaMA 7B on 6 GPUs
run: HSA=1 python3 examples/llama.py --gen 1 --size 7B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_six_gpu.txt
- name: Run LLaMA-2 70B
run: HSA=1 python3 examples/llama.py --gen 2 --size 70B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_2_70B.txt
- name: Run Mixtral 8x7B
@@ -176,6 +178,7 @@ jobs:
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt
llama_six_gpu.txt
llama_2_70B.txt
gpt2_unjitted.txt
gpt2_jitted.txt