github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-02 09:38:05 +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

4
tests/test_fx/test_codegen/test_activation_checkpoint_codegen.py
View File

@@ -64,7 +64,7 @@ class MyModule(torch.nn.Module):
def _run_act_ckpt_codegen(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and run forward
model = MyModule()
@@ -127,7 +127,7 @@ def test_act_ckpt_codegen():
def _run_act_ckpt_python_code_torch11(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and run forward
model = MyModule()

4
tests/test_fx/test_codegen/test_nested_activation_checkpoint_codegen.py
View File

@@ -32,7 +32,7 @@ class MyModule(torch.nn.Module):
def _run_act_ckpt_codegen(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and run forward
model = MyModule()
@@ -96,7 +96,7 @@ def test_act_ckpt_codegen():
def _run_act_ckpt_python_code_torch11(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and run forward
model = MyModule()

4
tests/test_fx/test_codegen/test_offload_codegen.py
View File

@@ -66,7 +66,7 @@ def _test_fwd_and_bwd(model: torch.nn.Module, gm: ColoGraphModule, data: torch.T
def _run_offload_codegen(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and input
model = MyNet().cuda()
@@ -124,7 +124,7 @@ def test_act_ckpt_codegen():
def _run_offload_codegen_torch11(rank, world_size, port):
# launch colossalai to make sure we could execute colossalai.utils.checkpoint currently
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
colossalai.launch(rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
# build model and input
model = MyNet().cuda()