github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-02-04 19:55:18 -05:00
Code Issues Packages Projects Releases Wiki Activity

enable llama 2 70B in tinybox green CI (#5905)

Browse Source 
runnable with MAX_CONTEXT=256
This commit is contained in:
chenyu
2024-08-04 18:48:46 -04:00
committed by GitHub
parent 4a65010de8
commit adba5efc64
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/benchmark.yml vendored
View File

@@ -188,8 +188,8 @@ jobs:
run: NV=1 python3 examples/llama3.py --shard 4 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_four_gpu.txt
- name: Run LLaMA-3 8B on 6 GPUs
run: NV=1 python3 examples/llama3.py --shard 6 --model weights/LLaMA-3/8B-SF-DPO/ --benchmark --temperature 0 | tee llama3_six_gpu.txt
# - name: Run LLaMA-2 70B
# run: CUDA=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 LLaMA-2 70B
run: NV=1 MAX_CONTEXT=256 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
run: time NV=1 python3 examples/mixtral.py --temperature 0 --count 10 --timing | tee mixtral.txt
- name: Run GPT2
@@ -220,7 +220,7 @@ jobs:
llama3_beam.txt
llama3_four_gpu.txt
llama3_six_gpu.txt
# llama_2_70B.txt
llama_2_70B.txt
mixtral.txt
gpt2_unjitted.txt
gpt2_jitted.txt