vllm
vllm copied to clipboard
Published
3 months ago
•
vllm-project
vllm-project
[Bug]: RuntimeError: LLMEngine should not be pickled!
Your current environment
The output of `python collect_env.py`
INFO 02-12 18:14:16 __init__.py:190] Automatically detected platform cuda.
Collecting environment information...
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 24.04.1 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: Could not collect
CMake version: version 3.28.3
Libc version: glibc-2.39
Python version: 3.12.3 (main, Jan 17 2025, 18:03:48) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-52-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090
Nvidia driver version: 550.144.03
cuDNN version: Could not collect
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: 43 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 12
On-line CPU(s) list: 0-11
Vendor ID: AuthenticAMD
Model name: AMD Ryzen 5 3600 6-Core Processor
CPU family: 23
Model: 113
Thread(s) per core: 2
Core(s) per socket: 6
Socket(s): 1
Stepping: 0
Frequency boost: enabled
CPU(s) scaling MHz: 76%
CPU max MHz: 4441,9922
CPU min MHz: 2200,0000
BogoMIPS: 7585,26
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 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy 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 hw_pstate ssbd mba ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
L1d cache: 192 KiB (6 instances)
L1i cache: 192 KiB (6 instances)
L2 cache: 3 MiB (6 instances)
L3 cache: 32 MiB (2 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-11
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 Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection
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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-ml-py==12.570.86
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.1
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.48.3
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.2
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-11 0 N/A
Legend:
X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLinks
LD_LIBRARY_PATH=/usr/local/cuda/lib64:
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
import re
from datasets import load_dataset, Dataset
from unsloth import FastLanguageModel, PatchFastRL, is_bfloat16_supported
from trl import GRPOConfig, GRPOTrainer
SYSTEM_PROMPT = """
Respond in the following format:
<reasoning>
...
</reasoning>
<answer>
...
</answer>
"""
XML_COT_FORMAT = """\
<reasoning>
{reasoning}
</reasoning>
<answer>
{answer}
</answer>
"""
MAX_SEQ_LENGTH = 1024
LORA_RANK = 64
def extract_xml_answer(text: str) -> str:
answer = text.split("<answer>")[-1]
answer = answer.split("</answer>")[0]
return answer.strip()
def extract_hash_answer(text: str) -> str | None:
if "####" not in text:
return None
return text.split("####")[1].strip()
def get_gsm8k_questions(split="train") -> Dataset:
data = load_dataset("openai/gsm8k", "main")[split]
data = data.map(
lambda x: {
"prompt": [
{"role": "system", "content": SYSTEM_PROMPT},
{"role": "user", "content": x["question"]},
],
"answer": extract_hash_answer(x["answer"]),
}
)
return data
# Reward functions remain the same...
def correctness_reward_func(prompts, completions, answer, **kwargs) -> list[float]:
responses = [completion[0]["content"] for completion in completions]
q = prompts[0][-1]["content"]
extracted_responses = [extract_xml_answer(r) for r in responses]
print(
"-" * 20,
f"Question:\n{q}",
f"\nAnswer:\n{answer[0]}",
f"\nResponse:\n{responses[0]}",
f"\nExtracted:\n{extracted_responses[0]}",
)
return [2.0 if r == a else 0.0 for r, a in zip(extracted_responses, answer)]
def int_reward_func(completions, **kwargs) -> list[float]:
responses = [completion[0]["content"] for completion in completions]
extracted_responses = [extract_xml_answer(r) for r in responses]
return [0.5 if r.isdigit() else 0.0 for r in extracted_responses]
def strict_format_reward_func(completions, **kwargs) -> list[float]:
pattern = r"^<reasoning>\n.*?\n</reasoning>\n<answer>\n.*?\n</answer>\n$"
responses = [completion[0]["content"] for completion in completions]
matches = [re.match(pattern, r) for r in responses]
return [0.5 if match else 0.0 for match in matches]
def soft_format_reward_func(completions, **kwargs) -> list[float]:
pattern = r"<reasoning>.*?</reasoning>\s*<answer>.*?</answer>"
responses = [completion[0]["content"] for completion in completions]
matches = [re.match(pattern, r) for r in responses]
return [0.5 if match else 0.0 for match in matches]
def count_xml(text) -> float:
count = 0.0
if text.count("<reasoning>\n") == 1:
count += 0.125
if text.count("\n</reasoning>\n") == 1:
count += 0.125
if text.count("\n<answer>\n") == 1:
count += 0.125
count -= len(text.split("\n</answer>\n")[-1]) * 0.001
if text.count("\n</answer>") == 1:
count += 0.125
count -= (len(text.split("\n</answer>")[-1]) - 1) * 0.001
return count
def xmlcount_reward_func(completions, **kwargs) -> list[float]:
contents = [completion[0]["content"] for completion in completions]
return [count_xml(c) for c in contents]
def main():
# Initialize dataset
dataset = get_gsm8k_questions()
# Patch FastRL
PatchFastRL("GRPO", FastLanguageModel)
# Initialize model and tokenizer
model, tokenizer = FastLanguageModel.from_pretrained(
model_name="Qwen/Qwen2.5-3B-Instruct",
max_seq_length=MAX_SEQ_LENGTH,
load_in_4bit=True,
fast_inference=True, # Disable vLLM to avoid pickling error
max_lora_rank=LORA_RANK,
gpu_memory_utilization=0.5,
)
# Get PEFT model
model = FastLanguageModel.get_peft_model(
model,
r=LORA_RANK,
target_modules=[
"gate_proj",
"up_proj",
"down_proj",
"q_proj",
"k_proj",
"v_proj",
"o_proj",
],
lora_alpha=LORA_RANK,
use_gradient_checkpointing="unsloth",
random_state=3407,
)
# Training configuration
training_args = GRPOConfig(
use_vllm=True, # Disable vLLM to avoid pickling error
learning_rate=5e-6,
adam_beta1=0.9,
adam_beta2=0.99,
weight_decay=0.1,
warmup_ratio=0.1,
lr_scheduler_type="cosine",
optim="adamw_8bit",
logging_steps=1,
bf16=is_bfloat16_supported(),
fp16=not is_bfloat16_supported(),
per_device_train_batch_size=1,
gradient_accumulation_steps=1,
num_generations=8,
max_prompt_length=256,
max_completion_length=200,
max_steps=250,
save_steps=250,
max_grad_norm=0.1,
report_to="none",
output_dir="outputs",
)
# Initialize trainer
trainer = GRPOTrainer(
model=model,
processing_class=tokenizer,
reward_funcs=[
xmlcount_reward_func,
soft_format_reward_func,
strict_format_reward_func,
int_reward_func,
correctness_reward_func,
],
args=training_args,
train_dataset=dataset,
)
# Train
trainer.train()
# Save the model
model.save_lora("grpo_saved_lora")
if __name__ == "__main__":
main()
🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning. 🦥 Unsloth Zoo will now patch everything to make training faster! INFO 02-12 18:09:51 init.py:190] Automatically detected platform cuda. ==((====))== Unsloth 2025.2.5: Fast Qwen2 patching. Transformers: 4.48.3. \ /| GPU: NVIDIA GeForce RTX 3090. Max memory: 23.683 GB. Platform: Linux. O^O/ _/ \ Torch: 2.5.1+cu124. CUDA: 8.6. CUDA Toolkit: 12.4. Triton: 3.1.0 \ / Bfloat16 = TRUE. FA [Xformers = 0.0.28.post3. FA2 = False] "-____-" Free Apache license: http://github.com/unslothai/unsloth Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored! Unsloth: vLLM loading unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit with actual GPU utilization = 49.07% Unsloth: Your GPU has CUDA compute capability 8.6 with VRAM = 23.68 GB. Unsloth: Using conservativeness = 1.0. Chunked prefill tokens = 1024. Num Sequences = 224. Unsloth: vLLM's KV Cache can use up to 9.2 GB. Also swap space = 4 GB. ....
[rank0]: RuntimeError: LLMEngine should not be pickled!
When disabled vLLM usage:
-
Set
fast_inference=Falsein the model initialization (FastLanguageModel.from_pretrained(...)) -
Set
use_vllm=Falsein the training configuration (GRPOConfig(...))
It's OK. No errors.
Before submitting a new issue...
- [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
Encountered the same issue, which was resolved by this: https://github.com/unslothai/unsloth/issues/1632#issuecomment-2642047973
Move PatchFastRL("GRPO", FastLanguageModel) before the remaining trl imports.
Encountered the same issue, which was resolved by this: unslothai/unsloth#1632 (comment)
Move
PatchFastRL("GRPO", FastLanguageModel)before the remainingtrlimports.
Awesome, thank you! This worked.
