From 08a1244ef1c8b53731637fe911f22b7f934cfc28 Mon Sep 17 00:00:00 2001 From: "pre-commit-ci[bot]" <66853113+pre-commit-ci[bot]@users.noreply.github.com> Date: Wed, 6 Aug 2025 06:16:37 +0000 Subject: [PATCH 1/5] [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --- applications/ColossalChat/coati/distributed/grpo_consumer.py | 2 +- colossalai/shardformer/modeling/qwen3.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/applications/ColossalChat/coati/distributed/grpo_consumer.py b/applications/ColossalChat/coati/distributed/grpo_consumer.py index a2c3e03d6..424d46098 100644 --- a/applications/ColossalChat/coati/distributed/grpo_consumer.py +++ b/applications/ColossalChat/coati/distributed/grpo_consumer.py @@ -530,4 +530,4 @@ class GRPOConsumer(BaseConsumer): model = self.policy_model.unwrap() state_dict = model.state_dict() state_dict["consumer_global_step"] = torch.tensor([self.global_step], device=self.device) - return state_dict \ No newline at end of file + return state_dict diff --git a/colossalai/shardformer/modeling/qwen3.py b/colossalai/shardformer/modeling/qwen3.py index 437693800..5f96f5f49 100644 --- a/colossalai/shardformer/modeling/qwen3.py +++ b/colossalai/shardformer/modeling/qwen3.py @@ -273,7 +273,7 @@ class Qwen3PipelineForwards: hidden_states: Optional[torch.FloatTensor] = None, stage_index: Optional[List[int]] = None, shard_config: ShardConfig = None, - **kwargs + **kwargs, ): r""" Args: From b6a5f678cdcfd36d869d47abd30ee3de108ca725 Mon Sep 17 00:00:00 2001 From: Hanks Date: Wed, 13 Aug 2025 16:37:49 +0800 Subject: [PATCH 2/5] reduce memory consumption --- .github/workflows/run_chatgpt_examples.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/run_chatgpt_examples.yml b/.github/workflows/run_chatgpt_examples.yml index f25a6189f..b8ce726fd 100644 --- a/.github/workflows/run_chatgpt_examples.yml +++ b/.github/workflows/run_chatgpt_examples.yml @@ -34,6 +34,10 @@ jobs: pip install --no-cache-dir -v -e . - name: Install ChatGPT + env: + CFLAGS: "-O0" + CXXFLAGS: "-O0" + MAX_JOBS: 4 run: | cd applications/ColossalChat pip install --no-cache-dir -v . From 9db9892f6311d776c71093e7b80315f3dfc2181a Mon Sep 17 00:00:00 2001 From: Hanks Date: Wed, 13 Aug 2025 16:45:43 +0800 Subject: [PATCH 3/5] reduce memory consumption --- .github/workflows/run_chatgpt_unit_tests.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/run_chatgpt_unit_tests.yml b/.github/workflows/run_chatgpt_unit_tests.yml index 9180ede37..a7862db49 100644 --- a/.github/workflows/run_chatgpt_unit_tests.yml +++ b/.github/workflows/run_chatgpt_unit_tests.yml @@ -30,6 +30,10 @@ jobs: uses: actions/checkout@v2 - name: Install ChatGPT + env: + CFLAGS: "-O0" + CXXFLAGS: "-O0" + MAX_JOBS: 4 run: | cd applications/ColossalChat pip install -v . From c83dc666450a2316f31373c31cc2ac9c56377d40 Mon Sep 17 00:00:00 2001 From: Hanks Date: Thu, 14 Aug 2025 09:39:49 +0800 Subject: [PATCH 4/5] Update timeout --- .github/workflows/run_chatgpt_unit_tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/run_chatgpt_unit_tests.yml b/.github/workflows/run_chatgpt_unit_tests.yml index a7862db49..5cbcaa7fb 100644 --- a/.github/workflows/run_chatgpt_unit_tests.yml +++ b/.github/workflows/run_chatgpt_unit_tests.yml @@ -21,7 +21,7 @@ jobs: container: image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0 options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data - timeout-minutes: 30 + timeout-minutes: 180 defaults: run: shell: bash @@ -31,8 +31,8 @@ jobs: - name: Install ChatGPT env: - CFLAGS: "-O0" - CXXFLAGS: "-O0" + CFLAGS: "-O1" + CXXFLAGS: "-O1" MAX_JOBS: 4 run: | cd applications/ColossalChat From 94e972fda6e6901de81cb4dadf6afbf68b04b43b Mon Sep 17 00:00:00 2001 From: Hanks Date: Thu, 14 Aug 2025 09:42:21 +0800 Subject: [PATCH 5/5] Update timeout --- .github/workflows/run_chatgpt_examples.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/run_chatgpt_examples.yml b/.github/workflows/run_chatgpt_examples.yml index b8ce726fd..119482536 100644 --- a/.github/workflows/run_chatgpt_examples.yml +++ b/.github/workflows/run_chatgpt_examples.yml @@ -21,7 +21,7 @@ jobs: container: image: image-cloud.luchentech.com/hpcaitech/pytorch-cuda:2.2.2-12.1.0 options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data --shm-size=10.24gb - timeout-minutes: 60 + timeout-minutes: 180 defaults: run: shell: bash @@ -35,8 +35,8 @@ jobs: - name: Install ChatGPT env: - CFLAGS: "-O0" - CXXFLAGS: "-O0" + CFLAGS: "-O1" + CXXFLAGS: "-O1" MAX_JOBS: 4 run: | cd applications/ColossalChat