github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-09 06:58:11 -05:00
Code Issues Packages Projects Releases Wiki Activity

7B llama on 4 gpus on benchmark (#3804)

Browse Source
This commit is contained in:
chenyu
2024-03-18 14:32:37 -04:00
committed by GitHub
parent d79a1d315b
commit 1711274654
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/benchmark.yml vendored
View File

@@ -159,6 +159,8 @@ jobs:
HSA=1 JIT=1 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_jitted.txt
- 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 4 GPUs
run: HSA=1 python3 examples/llama.py --gen 1 --size 7B --shard 4 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_four_gpu.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
@@ -178,6 +180,7 @@ jobs:
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt
llama_four_gpu.txt
llama_six_gpu.txt
llama_2_70B.txt
gpt2_unjitted.txt