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

add llama 2 70B in ci and verify output (#3682)

Browse Source 
* add llama 2 70B in ci and verify output

* ln -s llama2 dir
This commit is contained in:
chenyu
2024-03-11 12:48:22 -04:00
committed by GitHub
parent e10ee2ed3f
commit d69170e27e
2 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/benchmark.yml vendored
View File

@@ -140,6 +140,7 @@ jobs:
ln -s ~/tinygrad/weights/LLaMA weights/LLaMA
ln -s ~/tinygrad/extra/datasets/cifar-10-python.tar.gz extra/datasets/cifar-10-python.tar.gz
ln -s /raid/weights/mixtral-8x7b-32kseqlen weights/mixtral-8x7b-32kseqlen
ln -s /raid/weights/LLaMA-2 weights/LLaMA-2
- name: Run model inference benchmark
run: LD_PRELOAD="/opt/rocm/lib/libhsa-runtime64.so" HSA=1 NOCLANG=1 python3 test/external/external_model_benchmark.py
- name: Test speed vs torch
@@ -156,6 +157,8 @@ 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 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-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
run: time HSA=1 python3 examples/mixtral.py --temperature 0 --count 10 --timing | tee mixtral.txt
- name: Run GPT2
@@ -184,6 +187,7 @@ jobs:
llama_unjitted.txt
llama_jitted.txt
llama_beam.txt
llama_2_70B.txt
gpt2_unjitted.txt
gpt2_jitted.txt
matmul.txt