mirrors/tinygrad
2
0
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-06-24 02:14:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

metal CI run llama with 4 shards (#4103)

Browse source 
this can catch multi tensor issue on mac.
This commit is contained in:
chenyu 2024-04-07 11:04:08 -04:00 • committed by GitHub
commit 9a95d87366
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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

@ -44,6 +44,8 @@ jobs:
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: 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 (virtual) GPUs
run: JIT=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 GPT2
run: |
JIT=0 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt
@ -72,6 +74,7 @@ jobs:
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt
llama_four_gpu.txt
gpt2_unjitted.txt
gpt2_jitted.txt
gpt2_half.txt