github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-14 21:51:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] refactor launch API and tensor constructor (#5666)

Browse Source 
* [misc] remove config arg from initialize

* [misc] remove old tensor contrusctor

* [plugin] add npu support for ddp

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [devops] fix doc test ci

* [test] fix test launch

* [doc] update launch doc

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Hongxin Liu
2024-04-29 10:40:11 +08:00
committed by GitHub
parent 91fa553775
commit 7f8b16635b
223 changed files with 294 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/test_legacy/test_layers/test_1d/test_1d.py
View File

@@ -17,7 +17,7 @@ CONFIG = dict(
def check_layer(rank, world_size, port):
disable_existing_loggers()
launch(config=CONFIG, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
check_linear_col()
check_linear_row()

2
tests/test_legacy/test_layers/test_2d/test_2d.py
View File

@@ -50,7 +50,7 @@ def check_layer():
def check_layer_and_operation(rank, world_size, port):
disable_existing_loggers()
launch(config=CONFIG, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
torch.backends.cuda.matmul.allow_tf32 = False
torch.backends.cudnn.allow_tf32 = False

2
tests/test_legacy/test_layers/test_2p5d/test_2p5d.py
View File

@@ -38,7 +38,7 @@ def check_layer():
def check_layer_and_operation(rank, world_size, port):
disable_existing_loggers()
launch(config=CONFIG, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
torch.backends.cuda.matmul.allow_tf32 = False
torch.backends.cudnn.allow_tf32 = False

2
tests/test_legacy/test_layers/test_3d/test_3d.py
View File

@@ -44,7 +44,7 @@ def check_layer():
def check_layer_and_operation(rank, world_size, port):
disable_existing_loggers()
launch(config=CONFIG, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
torch.backends.cuda.matmul.allow_tf32 = False
torch.backends.cudnn.allow_tf32 = False
torch.backends.cudnn.deterministic = True

2
tests/test_legacy/test_layers/test_cache_embedding.py
View File

@@ -378,7 +378,7 @@ def run_parallel_freq_aware_embed_columnwise(rank, world_size):
def run_dist(rank, world_size, port):
colossalai.legacy.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.legacy.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# run_parallel_freq_aware_embed_columnwise(rank, world_size)
run_parallel_freq_aware_embed_tablewise(rank, world_size)