[Bug?] vLLMRollout.generate_sequences Randomly Hangs After 1-2 Steps When trying to Implement Tool Calling with Logits Processors #340
Description
I've tried the method of vLLMRollout.generate_sequences to implement tool calling with verl 0.2 and vllm 0.6.3, However, it randomly hangs after running for 1 to 2 steps. Specifically, the GPU utilization gets stuck at 100%, while the power consumption drops significantly low, and the logs stop updating.
Below is the code snippet I used:
my_tool_processor = FunctionProcessor(self.tokenizer)
sampling_params.logits_processors = [my_tool_processor]class FunctionProcessor:
def __init__(
self,
tokenizer,
start_tag: str = "<tool_call>",
end_tag: str = "</tool_call>",
result_start: str = "\n<tool_result>\n",
result_end: str = "\n</tool_result>\n<think>"
):
self.tokenizer = tokenizer
self.buffer = []
self.in_function = False
self.current_function = []
# Pre-tokenize markers
self.start_marker = tokenizer.encode(start_tag, add_special_tokens=False)[0]
self.end_marker = tokenizer.encode(end_tag, add_special_tokens=False)[0]
self.result_start = tokenizer.encode(result_start, add_special_tokens=False)
self.result_end = tokenizer.encode(result_end, add_special_tokens=False)
self.result_tokens = []
self.state_dict = {}
def evaluate_expression(self, expr: str) -> str:
try:
# get_tool_resp is the function that will be called to evaluate the expression, time cost no more than 3 seconds.
result = get_tool_resp(expr)
return str(result)
except Exception as e:
return f"Error: {str(e)}"
def __call__(self, input_ids: List[int], scores: torch.Tensor) -> torch.Tensor:
try:
if input_ids[-1] == self.end_marker:
idx = 1
while idx <= len(input_ids):
if input_ids[-idx] == self.start_marker:
if input_ids[-idx:].count(self.start_marker) > 1 or input_ids[-idx:].count(self.end_marker) > 1:
break
current_function = input_ids[-idx:]
func_text = self.tokenizer.decode(current_function)
try:
result = self.evaluate_expression(func_text)
except:
result = "{'result': 'Tool Call Error'}"
result_tokens = list(reversed(
self.result_start +
self.tokenizer.encode(str(result)) +
self.result_end
))
state_dict_key = tuple(input_ids)
self.state_dict[state_dict_key] = result_tokens
token_id = self.state_dict[state_dict_key].pop()
scores[token_id] = 100
break
idx += 1
else:
for idx in range(1, len(self.end_marker)):
if input_ids[-idx] == self.start_marker:
state_dict_key = tuple(input_ids[:-idx + 1])
result_tokens = self.state_dict.get(state_dict_key, [])
if result_tokens:
self.state_dict[state_dict_key] = result_tokens
token_id = self.state_dict[state_dict_key].pop()
scores[token_id] = 100
break
except Exception as e:
print(f"Error in FunctionProcessor: {e}")
return scoresEnv
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.5 LTS (x86_64)
GCC version: (GCC) 12.2.0
Clang version: 3.8.0 (tags/RELEASE_380/final)
CMake version: Could not collect
Libc version: glibc-2.31
Python version: 3.11.3 (main, Apr 5 2023, 14:15:06) [GCC 9.4.0] (64-bit runtime)
Python platform: Linux-5.10.0-2.0.0.2-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.4.99
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: CF-NG-HZZ1-O
GPU 1: CF-NG-HZZ1-O
GPU 2: CF-NG-HZZ1-O
GPU 3: CF-NG-HZZ1-O
GPU 4: CF-NG-HZZ1-O
GPU 5: CF-NG-HZZ1-O
GPU 6: CF-NG-HZZ1-O
GPU 7: CF-NG-HZZ1-O
Nvidia driver version: 535.183.06
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.0.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.0.0
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
Byte Order: Little Endian
Address sizes: 52 bits physical, 57 bits virtual
CPU(s): 192
On-line CPU(s) list: 0-191
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 143
Model name: Intel(R) Xeon(R) Platinum 8468V
Stepping: 8
CPU MHz: 2900.000
CPU max MHz: 3800.0000
CPU min MHz: 800.0000
BogoMIPS: 4800.00
Virtualization: VT-x
L1d cache: 4.5 MiB
L1i cache: 3 MiB
L2 cache: 192 MiB
L3 cache: 195 MiB
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers
Vulnerability Spectre v2: Vulnerable, IBPB: disabled, STIBP: disabled
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi avx512vbmi umip pku waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.1
[pip3] torch==2.4.0
[pip3] torchaudio==2.5.1
[pip3] torchvision==0.19.0
[pip3] transformers==4.47.1
[pip3] triton==3.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: N/A (dev)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 NODE NODE NODE NODE NODE PIX SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE NODE NODE NODE PIX NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE NODE PIX NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE PIX NODE NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS NODE PIX NODE NODE 48-95,144-191 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS PIX NODE NODE NODE 48-95,144-191 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS NODE NODE NODE PIX 48-95,144-191 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS NODE NODE PIX NODE 48-95,144-191 1 N/A
NIC0 NODE NODE NODE NODE SYS SYS SYS SYS X PIX NODE NODE NODE NODE SYS SYS SYS SYS
NIC1 NODE NODE NODE NODE SYS SYS SYS SYS PIX X NODE NODE NODE NODE SYS SYS SYS SYS
NIC2 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE X NODE NODE NODE SYS SYS SYS SYS
NIC3 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE SYS SYS SYS SYS
NIC4 NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE SYS SYS SYS SYS
NIC5 PIX NODE NODE NODE SYS SYS SYS SYS NODE NODE NODE NODE NODE X SYS SYS SYS SYS
NIC6 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS X NODE NODE NODE
NIC7 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS NODE X NODE NODE
NIC8 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS NODE NODE X NODE
NIC9 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS NODE NODE NODE X
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
NIC Legend:
NIC0: mlx5_0
NIC1: mlx5_1
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
NIC8: mlx5_8
NIC9: mlx5_9
NVIDIA_VISIBLE_DEVICES=GPU-00c17004-1a68-8b2e-bf1f-ce4a849177c9,GPU-50c603ba-d9c5-5c24-dfa1-610ef45f5dfe,GPU-38cdf56a-4962-87b6-f54e-3c591c3b6f94,GPU-e667f094-50f7-6a86-0173-98bc170da5d4,GPU-2fe323cd-e3ae-7915-1299-542a62e79926,GPU-f2c15f28-fdbf-499d-4d81-26545c14c0fd,GPU-89fd4b88-9a9e-7e89-b4fd-820425524007,GPU-b6221a29-7a6f-d2e5-fc50-2806885da539
NCCL_P2P_DISABLE=0
NVIDIA_REQUIRE_CUDA=cuda>=12.0 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516
NCCL_IB_CUDA_SUPPORT=0
NVIDIA_LIB=/usr/local/nvidia/lib64
NCCL_VERSION=2.17.1-1
NCCL_SOCKET_IFNAME=xgbe0
NCCL_DEBUG_SUBSYS=INIT,ENV,GRAPH
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NCCL_DEBUG=INFO
NVIDIA_PRODUCT_NAME=CUDA
NCCL_IB_GID_INDEX=3
CUDA_VERSION=12.0.1
NVIDIA_TOOLS=/home/opt/cuda_tools
NCCL_DEBUG_FILE=/root/workspace/log/nccl.%h.%p.log
NCCL_IB_QPS_PER_CONNECTION=2
NCCL_IB_CONNECT_RETRY_CNT=15
NCCL_ERROR_FILE=/root/workspace/log/err.%h.%p.log
NCCL_IB_TIMEOUT=22
CUDNN_VERSION=8.9.1
LD_LIBRARY_PATH=/root/venv/lib/python3.11/site-packages/cv2/../../lib64:/usr/local/lib:/usr/local/x86_64-pc-linux-gnu/lib:/home/opt/nvidia_lib:/usr/local/cuda/lib64:/usr/lib64:/usr/local/lib:/usr/lib/x86_64-linux-gnu/
NCCL_IB_DISABLE=0
NCCL_IB_ADAPTIVE_ROUTING=1
CUDA_MODULE_LOADING=LAZY