Skip to content

[BUG]: use_fp8=True in HybridParallelPlugin causes runtime error Expected both dimensions of mat2 to be divisible by 16 but got torch.Size([768, 2]) #6390

Open
#6393
Open
[BUG]: use_fp8=True in HybridParallelPlugin causes runtime error Expected both dimensions of mat2 to be divisible by 16 but got torch.Size([768, 2])#6390
#6393
Labels
bugSomething isn't working
@sdjasj

Description

@sdjasj
sdjasj
opened on Nov 7, 2025

Is there an existing issue for this bug?

  • I have searched the existing issues

The bug has not been fixed in the latest main branch

  • I have checked the latest main branch

Do you feel comfortable sharing a concise (minimal) script that reproduces the error? :)

Yes, I will share a minimal reproducible script.

🐛 Describe the bug

When I run the training example from https://colossalai.org/zh-Hans/docs/advanced_tutorials/train_gpt_using_hybrid_parallelism with the following configuration

plugin = HybridParallelPlugin(
    tp_size=1,
    pp_size=1,
    sp_size=1,
    use_fp8=True,
)

I encounter the following error: Expected both dimensions of mat2 to be divisible by 16 but got torch.Size([768, 2]). However, when I set use_fp8 to False in the configuration, the error disappears. Therefore, it seems that the issue may be caused by a bug related to the use_fp8 option.

Below is the Python training script main.py that can reproduce the error:

from functools import partial
import json
import os
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import colossalai
from colossalai.booster import Booster
from colossalai.nn.optimizer import HybridAdam
import datasets
from typing import Callable, Optional
import torch
import torch.nn as nn
from torch.optim import Optimizer
from torch.optim.lr_scheduler import _LRScheduler as LRScheduler
from tqdm import tqdm
from transformers import AutoConfig, GPT2ForSequenceClassification, get_linear_schedule_with_warmup
from transformers import AutoTokenizer

import colossalai
from colossalai.booster import Booster
from colossalai.booster.plugin import HybridParallelPlugin
from colossalai.cluster import DistCoordinator
from colossalai.nn.optimizer import HybridAdam


TEST_GEMINI = False
NUM_EPOCHS = 1
BATCH_SIZE = 32
LEARNING_RATE = 2.4e-5
WEIGHT_DECAY = 0.01
WARMUP_FRACTION = 0.1

def tokenize_batch(batch, tokenizer: Optional[AutoTokenizer] = None, max_length: int = 512):
    texts = [sample["sentence1"] + " " + sample["sentence2"] for sample in batch]
    labels = torch.tensor([sample["label"] for sample in batch], dtype=torch.long)
    encoded = tokenizer(
        texts,
        return_tensors="pt",
        padding="max_length",
        truncation=True,
        max_length=max_length,
    )
    data = {k: v for k, v in encoded.items()}
    data["labels"] = labels
    return data


def move_to_cuda(data):
    if isinstance(data, torch.Tensor):
        return data.cuda()
    elif isinstance(data, dict):
        return {k: move_to_cuda(v) for k, v in data.items()}
    elif isinstance(data, list):
        return [move_to_cuda(v) for v in data]
    else:
        return data

def train_epoch(
    epoch: int,
    model: nn.Module,
    optimizer: Optimizer,
    _criterion: Callable,
    lr_scheduler: LRScheduler,
    train_dataloader: DataLoader,
    booster: Booster,
    coordinator: DistCoordinator,
):
    use_pipeline = isinstance(booster.plugin, HybridParallelPlugin) and booster.plugin.pp_size > 1
    is_pp_last_stage = use_pipeline and booster.plugin.stage_manager.is_last_stage()
    print_flag = (not use_pipeline and coordinator.is_master()) or (use_pipeline and is_pp_last_stage)
    total_step = len(train_dataloader)
    precision = getattr(booster.plugin, "precision", "fp16")
    dtype_map = {"fp16": torch.float16, "bf16": torch.bfloat16, "fp32": torch.float32}
    dtype = dtype_map.get(precision, torch.float16)

    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model.train()
    optimizer.zero_grad()
    train_dataloader_iter = iter(train_dataloader)
    with tqdm(
        range(total_step),
        desc=f"Epoch [{epoch + 1}/{NUM_EPOCHS}]",
        disable=not print_flag,
    ) as pbar:
        for step in pbar:
            if use_pipeline:
                outputs = booster.execute_pipeline(
                    train_dataloader_iter, model, _criterion, optimizer, return_loss=True
                )
                if is_pp_last_stage:
                    loss = outputs["loss"]
                    pbar.set_postfix({"loss": loss.item()})
            else:
                data = next(train_dataloader_iter)
                data = move_to_cuda(data)
                outputs = model(**data)
                loss = _criterion(outputs, None)
                booster.backward(loss, optimizer)
                pbar.set_postfix({"loss": loss.item()})

            optimizer.step()
            optimizer.zero_grad()
            lr_scheduler.step()
            if step >= 20:
                print(f"[Rank {coordinator.rank}] Early stop at step {step + 1}")
                break


def main():
    colossalai.launch_from_torch(seed=42)
    coordinator = DistCoordinator()
    plugin = HybridParallelPlugin(
        tp_size=1,
        pp_size=1,
        sp_size=1,
        use_fp8=True,
    )

    tokenizer = AutoTokenizer.from_pretrained("gpt2")
    tokenizer.pad_token = tokenizer.eos_token
    dataset = datasets.load_dataset("glue", "mrpc")
    train_dataloader = plugin.prepare_dataloader(
        dataset["train"],
        batch_size=BATCH_SIZE,
        shuffle=True,
        drop_last=True,
        collate_fn=partial(tokenize_batch, tokenizer=tokenizer, max_length=512),
    )
    config = AutoConfig.from_pretrained("gpt2", num_labels=2)
    config.pad_token_id = tokenizer.pad_token_id
    model = GPT2ForSequenceClassification.from_pretrained("gpt2", config=config).cuda()
    lr = LEARNING_RATE * coordinator.world_size
    no_decay = ["bias", "LayerNorm.weight"]
    optimizer_grouped_parameters = [
        {
            "params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)],
            "weight_decay": WEIGHT_DECAY,
        },
        {
            "params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)],
            "weight_decay": 0.0,
        },
    ]
    optimizer = HybridAdam(optimizer_grouped_parameters, lr=lr, eps=1e-8)
    total_steps = len(train_dataloader) * NUM_EPOCHS
    num_warmup_steps = int(WARMUP_FRACTION * total_steps)
    lr_scheduler = get_linear_schedule_with_warmup(
        optimizer,
        num_warmup_steps=num_warmup_steps,
        num_training_steps=total_steps,
    )

    def _criterion(outputs, inputs):
        return outputs.loss
    optimizer = HybridAdam(optimizer_grouped_parameters, lr=lr, eps=1e-8)
    booster = Booster(plugin=plugin)
    model, optimizer, _criterion, _, lr_scheduler = booster.boost(
        model, optimizer, criterion=_criterion, lr_scheduler=lr_scheduler
    )
    for epoch in range(NUM_EPOCHS):
        train_epoch(epoch, model, optimizer, _criterion, lr_scheduler, train_dataloader, booster, coordinator)


if __name__ == "__main__":
    main()

Running the following command:

colossalai run --nproc_per_node 4 main.py

Produces the following error log:

[rank2]: Traceback (most recent call last):
[rank2]:   File "/home/yanzhen/distributed_test/colossalAI/test/bug5.py", line 166, in <module>
[rank2]:     main()
[rank2]:   File "/home/yanzhen/distributed_test/colossalAI/test/bug5.py", line 162, in main
[rank2]:     train_epoch(epoch, model, optimizer, _criterion, lr_scheduler, train_dataloader, booster, coordinator)
[rank2]:   File "/home/yanzhen/distributed_test/colossalAI/test/bug5.py", line 97, in train_epoch
[rank2]:     outputs = model(**data)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank2]:     return self._call_impl(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank2]:     return forward_call(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/booster/plugin/hybrid_parallel_plugin.py", line 222, in forward
[rank2]:     return super().forward(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/interface/model.py", line 127, in forward
[rank2]:     return self.module(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank2]:     return self._call_impl(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank2]:     return forward_call(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1643, in forward
[rank2]:     else self._run_ddp_forward(*inputs, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1459, in _run_ddp_forward
[rank2]:     return self.module(*inputs, **kwargs)  # type: ignore[index]
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank2]:     return self._call_impl(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank2]:     return forward_call(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/transformers/models/gpt2/modeling_gpt2.py", line 1389, in forward
[rank2]:     logits = self.score(hidden_states)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank2]:     return self._call_impl(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank2]:     return forward_call(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 125, in forward
[rank2]:     return F.linear(input, self.weight, self.bias)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/tensor/colo_parameter.py", line 66, in __torch_function__
[rank2]:     ret = super().__torch_function__(func, types, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/tensor/colo_tensor.py", line 91, in __torch_function__
[rank2]:     ret = func(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/quantization/fp8.py", line 845, in linear_fp8
[rank2]:     out = _linear_fp8(input, weight, bias)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
[rank2]:     return fn(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 1263, in __call__
[rank2]:     return hijacked_callback(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
[rank2]:     result = self._inner_convert(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
[rank2]:     return _compile(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
[rank2]:     guarded_code = compile_inner(code, one_graph, hooks, transform)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
[rank2]:     return _compile_inner(code, one_graph, hooks, transform)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_utils_internal.py", line 87, in wrapper_function
[rank2]:     return function(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
[rank2]:     out_code = transform_code_object(code, transform)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
[rank2]:     transformations(instructions, code_options)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 219, in _fn
[rank2]:     return fn(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/convert_frame.py", line 634, in transform
[rank2]:     tracer.run()
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 2796, in run
[rank2]:     super().run()
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 983, in run
[rank2]:     while self.step():
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 895, in step
[rank2]:     self.dispatch_table[inst.opcode](self, inst)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 582, in wrapper
[rank2]:     return inner_fn(self, inst)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 1602, in CALL_FUNCTION
[rank2]:     self.call_function(fn, args, {})
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 830, in call_function
[rank2]:     self.push(fn.call_function(self, args, kwargs))  # type: ignore[arg-type]
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/misc.py", line 1024, in call_function
[rank2]:     return self.obj.call_method(tx, self.name, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/misc.py", line 774, in call_method
[rank2]:     return self.call_apply(tx, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/misc.py", line 694, in call_apply
[rank2]:     val = AutogradFunctionApplyVariable(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/higher_order_ops.py", line 2015, in call_function
[rank2]:     (fwd_out, _), fwd_graph, fwd_freevars = speculate_subgraph(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/higher_order_ops.py", line 462, in speculate_subgraph
[rank2]:     output = f.call_function(tx, args, sub_kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/functions.py", line 324, in call_function
[rank2]:     return super().call_function(tx, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/functions.py", line 111, in call_function
[rank2]:     return tx.inline_user_function_return(self, [*self.self_args(), *args], kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 836, in inline_user_function_return
[rank2]:     return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 3011, in inline_call
[rank2]:     return cls.inline_call_(parent, func, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 3139, in inline_call_
[rank2]:     tracer.run()
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 983, in run
[rank2]:     while self.step():
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 895, in step
[rank2]:     self.dispatch_table[inst.opcode](self, inst)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 582, in wrapper
[rank2]:     return inner_fn(self, inst)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 1692, in CALL_FUNCTION_KW
[rank2]:     self.call_function(fn, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/symbolic_convert.py", line 830, in call_function
[rank2]:     self.push(fn.call_function(self, args, kwargs))  # type: ignore[arg-type]
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/torch.py", line 897, in call_function
[rank2]:     tensor_variable = wrap_fx_proxy(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/builder.py", line 2037, in wrap_fx_proxy
[rank2]:     return wrap_fx_proxy_cls(target_cls=TensorVariable, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/variables/builder.py", line 2124, in wrap_fx_proxy_cls
[rank2]:     example_value = get_fake_value(proxy.node, tx, allow_non_graph_fake=True)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 2082, in get_fake_value
[rank2]:     raise TorchRuntimeError(str(e)).with_traceback(e.__traceback__) from None
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 2017, in get_fake_value
[rank2]:     ret_val = wrap_fake_exception(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 1574, in wrap_fake_exception
[rank2]:     return fn()
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 2018, in <lambda>
[rank2]:     lambda: run_node(tx.output, node, args, kwargs, nnmodule)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 2150, in run_node
[rank2]:     raise RuntimeError(make_error_message(e)).with_traceback(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_dynamo/utils.py", line 2132, in run_node
[rank2]:     return node.target(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/utils/_stats.py", line 21, in wrapper
[rank2]:     return fn(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_subclasses/fake_tensor.py", line 1238, in __torch_dispatch__
[rank2]:     return self.dispatch(func, types, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_subclasses/fake_tensor.py", line 1692, in dispatch
[rank2]:     return self._cached_dispatch_impl(func, types, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_subclasses/fake_tensor.py", line 1339, in _cached_dispatch_impl
[rank2]:     output = self._dispatch_impl(func, types, args, kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_subclasses/fake_tensor.py", line 2013, in _dispatch_impl
[rank2]:     r = func(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_ops.py", line 716, in __call__
[rank2]:     return self._op(*args, **kwargs)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/_meta_registrations.py", line 5633, in meta_scaled_mm
[rank2]:     torch._check(
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/__init__.py", line 1564, in _check
[rank2]:     _check_with(RuntimeError, cond, message)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/__init__.py", line 1546, in _check_with
[rank2]:     raise error_type(message_evaluated)
[rank2]: torch._dynamo.exc.TorchRuntimeError: Failed running call_function <built-in method _scaled_mm of type object at 0x7f148b8ca1c0>(*(FakeTensor(..., device='cuda:2', size=(16384, 768), dtype=torch.float8_e4m3fn,
[rank2]:            grad_fn=<ToCopyBackward0>), FakeTensor(..., device='cuda:2', size=(768, 2), dtype=torch.float8_e4m3fn,
[rank2]:            grad_fn=<TBackward0>)), **{'bias': None, 'out_dtype': torch.float16, 'scale_a': FakeTensor(..., device='cuda:2', size=(1,), grad_fn=<UnsqueezeBackward0>), 'scale_b': FakeTensor(..., device='cuda:2', size=(1,), grad_fn=<UnsqueezeBackward0>), 'use_fast_accum': True}):
[rank2]: Expected both dimensions of mat2 to be divisble by 16 but got torch.Size([768, 2])

[rank2]: from user code:
[rank2]:    File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/quantization/fp8.py", line 839, in _linear_fp8
[rank2]:     return _LinearFp8.apply(input, weight, bias)
[rank2]:   File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/colossalai/quantization/fp8.py", line 800, in forward
[rank2]:     out = torch._scaled_mm(

[rank2]: Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information


[rank2]: You can suppress this exception and fall back to eager by setting:
[rank2]:     import torch._dynamo
[rank2]:     torch._dynamo.config.suppress_errors = True

[rank0]:[W1107 12:07:34.077140299 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present,  but this warning has only been added since PyTorch 2.4 (function operator())
W1107 12:07:35.104052 2974322 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2974402 closing signal SIGTERM
W1107 12:07:35.104708 2974322 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2974404 closing signal SIGTERM
W1107 12:07:35.107248 2974322 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 2974405 closing signal SIGTERM
E1107 12:07:35.286882 2974322 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 1 (pid: 2974403) of binary: /home/yanzhen/miniconda3/envs/colossal/bin/python3.9
Traceback (most recent call last):
  File "/home/yanzhen/miniconda3/envs/colossal/bin/torchrun", line 7, in <module>
    sys.exit(main())
  File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
    return f(*args, **kwargs)
  File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/distributed/run.py", line 919, in main
    run(args)
  File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/distributed/run.py", line 910, in run
    elastic_launch(
  File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/home/yanzhen/miniconda3/envs/colossal/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
============================================================
bug5.py FAILED
------------------------------------------------------------
Failures:
  <NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2025-11-07_12:07:35
  host      : ubuntu
  rank      : 1 (local_rank: 1)
  exitcode  : 1 (pid: 2974403)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
Error: failed to run torchrun --nproc_per_node=4 --nnodes=1 --node_rank=0 --master_addr=127.0.0.1 --master_port=29505 bug5.py on 127.0.0.1, is localhost: True, exception: Encountered a bad command exit code!

Command: 'cd /home/yanzhen/distributed_test/colossalAI/test && export SHELL="/bin/bash" COLORTERM="truecolor" VSCODE_DEBUGPY_ADAPTER_ENDPOINTS="/home/yanzhen/.vscode-server/extensions/ms-python.debugpy-2025.14.1/.noConfigDebugAdapterEndpoints/endpoint-8ca95acfe78cb59c.txt" TERM_PROGRAM_VERSION="1.105.1" CONDA_EXE="/home/yanzhen/miniconda3/bin/conda" NCCL_P2P_DISABLE="1" LC_ADDRESS="zh_CN.UTF-8" LC_NAME="zh_CN.UTF-8" PYDEVD_DISABLE_FILE_VALIDATION="1" LC_MONETARY="zh_CN.UTF-8" PWD="/home/yanzhen/distributed_test/colossalAI/test" LOGNAME="yanzhen" XDG_SESSION_TYPE="tty" CONDA_PREFIX="/home/yanzhen/miniconda3/envs/colossal" BUNDLED_DEBUGPY_PATH="/home/yanzhen/.vscode-server/extensions/ms-python.debugpy-2025.14.1/bundled/libs/debugpy" VSCODE_GIT_ASKPASS_NODE="/home/yanzhen/.vscode-server/cli/servers/Stable-7d842fb85a0275a4a8e4d7e040d2625abbf7f084/server/node" MOTD_SHOWN="pam" HOME="/home/yanzhen" LC_PAPER="zh_CN.UTF-8" LANG="en_US.UTF-8" LS_COLORS="rs=0:di=01;34:ln=01;36:mh=00:pi=40;33:so=01;35:do=01;35:bd=40;33;01:cd=40;33;01:or=40;31;01:mi=00:su=37;41:sg=30;43:ca=30;41:tw=30;42:ow=34;42:st=37;44:ex=01;32:*.tar=01;31:*.tgz=01;31:*.arc=01;31:*.arj=01;31:*.taz=01;31:*.lha=01;31:*.lz4=01;31:*.lzh=01;31:*.lzma=01;31:*.tlz=01;31:*.txz=01;31:*.tzo=01;31:*.t7z=01;31:*.zip=01;31:*.z=01;31:*.dz=01;31:*.gz=01;31:*.lrz=01;31:*.lz=01;31:*.lzo=01;31:*.xz=01;31:*.zst=01;31:*.tzst=01;31:*.bz2=01;31:*.bz=01;31:*.tbz=01;31:*.tbz2=01;31:*.tz=01;31:*.deb=01;31:*.rpm=01;31:*.jar=01;31:*.war=01;31:*.ear=01;31:*.sar=01;31:*.rar=01;31:*.alz=01;31:*.ace=01;31:*.zoo=01;31:*.cpio=01;31:*.7z=01;31:*.rz=01;31:*.cab=01;31:*.wim=01;31:*.swm=01;31:*.dwm=01;31:*.esd=01;31:*.jpg=01;35:*.jpeg=01;35:*.mjpg=01;35:*.mjpeg=01;35:*.gif=01;35:*.bmp=01;35:*.pbm=01;35:*.pgm=01;35:*.ppm=01;35:*.tga=01;35:*.xbm=01;35:*.xpm=01;35:*.tif=01;35:*.tiff=01;35:*.png=01;35:*.svg=01;35:*.svgz=01;35:*.mng=01;35:*.pcx=01;35:*.mov=01;35:*.mpg=01;35:*.mpeg=01;35:*.m2v=01;35:*.mkv=01;35:*.webm=01;35:*.webp=01;35:*.ogm=01;35:*.mp4=01;35:*.m4v=01;35:*.mp4v=01;35:*.vob=01;35:*.qt=01;35:*.nuv=01;35:*.wmv=01;35:*.asf=01;35:*.rm=01;35:*.rmvb=01;35:*.flc=01;35:*.avi=01;35:*.fli=01;35:*.flv=01;35:*.gl=01;35:*.dl=01;35:*.xcf=01;35:*.xwd=01;35:*.yuv=01;35:*.cgm=01;35:*.emf=01;35:*.ogv=01;35:*.ogx=01;35:*.aac=00;36:*.au=00;36:*.flac=00;36:*.m4a=00;36:*.mid=00;36:*.midi=00;36:*.mka=00;36:*.mp3=00;36:*.mpc=00;36:*.ogg=00;36:*.ra=00;36:*.wav=00;36:*.oga=00;36:*.opus=00;36:*.spx=00;36:*.xspf=00;36:" PYTHONSTARTUP="/home/yanzhen/.vscode-server/data/User/workspaceStorage/0d3e22743b5008777912953212595ae2/ms-python.python/pythonrc.py" SSL_CERT_DIR="/usr/lib/ssl/certs" CONDA_PROMPT_MODIFIER="(colossal) " GIT_ASKPASS="/home/yanzhen/.vscode-server/cli/servers/Stable-7d842fb85a0275a4a8e4d7e040d2625abbf7f084/server/extensions/git/dist/askpass.sh" SSH_CONNECTION="192.168.1.29 39642 192.168.102.133 18022" USE_MODELSCOPE_HUB="1" VSCODE_PYTHON_AUTOACTIVATE_GUARD="1" _CONDA_EXE="/home/yanzhen/miniconda3/bin/conda" LESSCLOSE="/usr/bin/lesspipe %s %s" _CONDA_ROOT="/home/yanzhen/miniconda3" XDG_SESSION_CLASS="user" TERM="xterm-256color" LC_IDENTIFICATION="zh_CN.UTF-8" PYTHON_BASIC_REPL="1" LESSOPEN="| /usr/bin/lesspipe %s" USER="yanzhen" VSCODE_GIT_IPC_HANDLE="/run/user/1006/vscode-git-760712a092.sock" CONDA_SHLVL="2" SHLVL="1" LC_TELEPHONE="zh_CN.UTF-8" LC_MEASUREMENT="zh_CN.UTF-8" XDG_SESSION_ID="6320" CONDA_PYTHON_EXE="/home/yanzhen/miniconda3/bin/python" LD_LIBRARY_PATH="/home/yanzhen/.tensornvme/lib:/usr/local/cuda-12.4/lib64:/home/yanzhen/.tensornvme/lib:/usr/local/cuda-12.4/lib64:" XDG_RUNTIME_DIR="/run/user/1006" SSL_CERT_FILE="/usr/lib/ssl/cert.pem" SSH_CLIENT="192.168.1.29 39642 18022" CONDA_DEFAULT_ENV="colossal" DEBUGINFOD_URLS="https://debuginfod.ubuntu.com " LC_TIME="zh_CN.UTF-8" VSCODE_GIT_ASKPASS_MAIN="/home/yanzhen/.vscode-server/cli/servers/Stable-7d842fb85a0275a4a8e4d7e040d2625abbf7f084/server/extensions/git/dist/askpass-main.js" CUDA_HOME="/usr/local/cuda-12.4" XDG_DATA_DIRS="/usr/share/gnome:/usr/local/share:/usr/share:/var/lib/snapd/desktop" BROWSER="/home/yanzhen/.vscode-server/cli/servers/Stable-7d842fb85a0275a4a8e4d7e040d2625abbf7f084/server/bin/helpers/browser.sh" PATH="/usr/local/cuda-12.4/bin:/home/yanzhen/.vscode-server/cli/servers/Stable-7d842fb85a0275a4a8e4d7e040d2625abbf7f084/server/bin/remote-cli:/home/yanzhen/.local/bin:/home/yanzhen/miniconda3/envs/colossal/bin:/home/yanzhen/miniconda3/condabin:/usr/local/cuda-12.4/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/home/yanzhen/miniconda3/bin:/home/yanzhen/.vscode-server/extensions/ms-python.debugpy-2025.14.1/bundled/scripts/noConfigScripts:/home/yanzhen/.vscode-server/data/User/globalStorage/github.copilot-chat/debugCommand:/home/yanzhen/miniconda3/bin" DBUS_SESSION_BUS_ADDRESS="unix:path=/run/user/1006/bus" CONDA_PREFIX_1="/home/yanzhen/miniconda3" LC_NUMERIC="zh_CN.UTF-8" TERM_PROGRAM="vscode" VSCODE_IPC_HOOK_CLI="/run/user/1006/vscode-ipc-d6a0f812-564d-488a-8d89-54d8df9c7838.sock" OLDPWD="/home/yanzhen/distributed_test" _="/home/yanzhen/miniconda3/envs/colossal/bin/colossalai" CUDA_DEVICE_MAX_CONNECTIONS="1" && torchrun --nproc_per_node=4 --nnodes=1 --node_rank=0 --master_addr=127.0.0.1 --master_port=29505 bug5.py'

Exit code: 1

Stdout: already printed

Stderr: already printed



====== Training on All Nodes =====
127.0.0.1: failure

====== Stopping All Nodes =====
127.0.0.1: finish

Environment

PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
Clang version: 18.1.3 (1ubuntu1)
CMake version: version 3.28.3
Libc version: glibc-2.39

Python version: 3.9.23 (main, Jun  5 2025, 13:40:20)  [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.5.0-18-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.4.99
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA GeForce RTX 4090
GPU 1: NVIDIA GeForce RTX 4090
GPU 2: NVIDIA GeForce RTX 4090
GPU 3: NVIDIA GeForce RTX 4090

Nvidia driver version: 580.65.06
cuDNN version: Probably one of the following:
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_adv_train.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8
/usr/local/cuda-11.6/targets/x86_64-linux/lib/libcudnn_ops_train.so.8
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      48 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             256
On-line CPU(s) list:                0-255
Vendor ID:                          AuthenticAMD
Model name:                         AMD EPYC 7773X 64-Core Processor
CPU family:                         25
Model:                              1
Thread(s) per core:                 2
Core(s) per socket:                 64
Socket(s):                          2
Stepping:                           2
Frequency boost:                    enabled
CPU max MHz:                        3527.7339
CPU min MHz:                        1500.0000
BogoMIPS:                           4400.15
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm
Virtualization:                     AMD-V
L1d cache:                          4 MiB (128 instances)
L1i cache:                          4 MiB (128 instances)
L2 cache:                           64 MiB (128 instances)
L3 cache:                           1.5 GiB (16 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-63,128-191
NUMA node1 CPU(s):                  64-127,192-255
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Not affected
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Mitigation; safe RET
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] galore-torch==1.0
[pip3] numpy==2.0.2
[pip3] torch==2.5.1
[pip3] triton==3.1.0
[conda] galore-torch                 1.0              pypi_0           pypi
[conda] numpy                        2.0.2            pypi_0           pypi
[conda] torch                        2.5.1            pypi_0           pypi
[conda] triton                       3.1.0            pypi_0           pypi

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions