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

revert the removal of CAST_BEFORE_VIEW (#4471)

Browse Source 
this brings most of the memory gain for resnet back.
This commit is contained in:
chenyu
2024-05-08 00:14:29 -04:00
committed by GitHub
parent 5dbab7fae6
commit c508eb7425
3 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -57,7 +57,7 @@ jobs:
run: JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half.txt
# TODO: this is flaky
# - name: Run GPT2 w HALF/BEAM
# run: JIT=0 HALF=1 BEAM=2 CACHELEVEL=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
# run: JIT=0 HALF=1 BEAM=2 CACHELEVEL=0 CAST_BEFORE_VIEW=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
- name: Train MNIST
run: time PYTHONPATH=. TARGET_EVAL_ACC_PCT=97.3 python3 examples/beautiful_mnist.py | tee beautiful_mnist.txt
- name: Run 10 CIFAR training steps
@@ -142,7 +142,7 @@ jobs:
- name: Run GPT2 w HALF
run: CUDA=1 JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half.txt
- name: Run GPT2 w HALF/BEAM
run: CUDA=1 JIT=1 HALF=1 BEAM=2 CACHELEVEL=0 JIT_BATCH_SIZE=4 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
run: CUDA=1 JIT=1 HALF=1 BEAM=2 CACHELEVEL=0 CAST_BEFORE_VIEW=0 JIT_BATCH_SIZE=4 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
- name: Train MNIST
run: time PYTHONPATH=. CUDA=1 TARGET_EVAL_ACC_PCT=97.3 python3 examples/beautiful_mnist.py | tee beautiful_mnist.txt
- name: Run 10 CIFAR training steps