github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-02 17:46:42 +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

3
tests/test_checkpoint_io/test_gemini_checkpoint_io.py
View File

@@ -173,8 +173,7 @@ def exam_lazy_from_pretrained():
def run_dist(rank, world_size, port):
config = {}
colossalai.launch(config=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")
exam_state_dict()
exam_state_dict_with_origin()
exam_lazy_from_pretrained()

3
tests/test_checkpoint_io/test_gemini_torch_compability.py
View File

@@ -163,8 +163,7 @@ def exam_gemini_load_from_torch(shard: bool, model_name: str):
def run_dist(rank, world_size, port):
config = {}
colossalai.launch(config=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")
exam_torch_load_from_gemini()
exam_gemini_load_from_torch()

3
tests/test_checkpoint_io/test_hybrid_parallel_plugin_checkpoint_io.py
View File

@@ -132,8 +132,7 @@ def exam_state_dict(shard: bool, model_name: str, size_per_shard: int, test_conf
def run_dist(rank, world_size, port):
config = {}
colossalai.launch(config=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")
exam_state_dict()

2
tests/test_checkpoint_io/test_low_level_zero_checkpoint_io.py
View File

@@ -172,7 +172,7 @@ def check_low_level_zero_lora_checkpointIO(
def run_dist(rank, world_size, port):
colossalai.launch(config=(dict()), rank=rank, world_size=world_size, port=port, host="localhost")
colossalai.launch(rank=rank, world_size=world_size, port=port, host="localhost")
check_low_level_zero_checkpointIO()
check_low_level_zero_lora_checkpointIO()
torch.cuda.empty_cache()

3
tests/test_checkpoint_io/test_plugins_huggingface_compatibility.py
View File

@@ -68,8 +68,7 @@ def exam_from_pretrained(plugin_type: str, model_name: str, shard=True, size_per
def run_dist(rank, world_size, port):
config = {}
colossalai.launch(config=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")
exam_from_pretrained()

2
tests/test_checkpoint_io/test_torch_ddp_checkpoint_io.py
View File

@@ -61,7 +61,7 @@ def check_torch_ddp_checkpointIO(shard: bool, size_per_shard: int):
def run_dist(rank, world_size, port):
colossalai.launch(config=(dict()), rank=rank, world_size=world_size, port=port, host="localhost")
colossalai.launch(rank=rank, world_size=world_size, port=port, host="localhost")
check_torch_ddp_checkpointIO()

2
tests/test_checkpoint_io/test_torch_fsdp_checkpoint_io.py
View File

@@ -141,7 +141,7 @@ def check_torch_fsdp_ckpt():
def run_dist(rank, world_size, port):
# init dist env
colossalai.launch(config=dict(), rank=rank, world_size=world_size, port=port, host="localhost")
colossalai.launch(rank=rank, world_size=world_size, port=port, host="localhost")
check_torch_fsdp_ckpt()