“I am unable to start this model using vllm serve on the RTX 5090.”
(Worker_TP0 pid=2590738) INFO 12-03 13:49:20 [default_loader.py:308] Loading weights took 12.22 seconds
(Worker_TP0 pid=2590738) INFO 12-03 13:49:21 [gpu_model_runner.py:3551] Model loading took 11.3354 GiB memory and 15.234166 seconds
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] WorkerProc hit an exception.
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] WorkerProc hit an exception.
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] Traceback (most recent call last):
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] Traceback (most recent call last):
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/vllm/vllm/v1/executor/multiproc_executor.py", line 817, in worker_busy_loop
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/vllm/vllm/v1/executor/multiproc_executor.py", line 817, in worker_busy_loop
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] output = func(*args, **kwargs)
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] output = func(*args, **kwargs)
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/frp_0.58.0_linux_amd64/GLM-4.5-Air-REAP-82B-A12B-nvfp4/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/frp_0.58.0_linux_amd64/GLM-4.5-Air-REAP-82B-A12B-nvfp4/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] return func(*args, **kwargs)
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] return func(*args, **kwargs)
(Worker_TP3 pid=2590741) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/vllm/vllm/v1/worker/gpu_worker.py", line 324, in determine_available_memory
(Worker_TP0 pid=2590738) ERROR 12-03 13:49:22 [multiproc_executor.py:822] File "/home/ubuntu/vllm/vllm/v1/worker/gpu_worker.py", line 324, in determine_available_memory
Above is part of the error message.
I want to know whether this model can run on an RTX 5090 using vllm.
my current environment
Collecting environment information...
System Info
==============================
OS : Ubuntu 22.04.5 LTS (x86_64)
GCC version : (Ubuntu 12.3.0-1ubuntu1~22.04.2) 12.3.0
Clang version : Could not collect
CMake version : version 4.2.0
Libc version : glibc-2.35
==============================
PyTorch Info
PyTorch version : 2.10.0.dev20251124+cu128
Is debug build : False
CUDA used to build PyTorch : 12.8
ROCM used to build PyTorch : N/A
==============================
Python Environment
Python version : 3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-6.8.0-87-generic-x86_64-with-glibc2.35
==============================
CUDA / GPU Info
Is CUDA available : True
CUDA runtime version : 12.8.93
CUDA_MODULE_LOADING set to :
GPU models and configuration :
GPU 0: NVIDIA GeForce RTX 5090
GPU 1: NVIDIA GeForce RTX 5090
GPU 2: NVIDIA GeForce RTX 5090
GPU 3: NVIDIA GeForce RTX 5090
Nvidia driver version : 570.172.08
cuDNN version : Could not collect
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 112
On-line CPU(s) list: 0-111
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6330 CPU @ 2.00GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 28
Socket(s): 2
Stepping: 6
CPU max MHz: 3100.0000
CPU min MHz: 800.0000
BogoMIPS: 4000.00
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 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 intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 2.6 MiB (56 instances)
L1i cache: 1.8 MiB (56 instances)
L2 cache: 70 MiB (56 instances)
L3 cache: 84 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-27,56-83
NUMA node1 CPU(s): 28-55,84-111
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Not affected
==============================
Versions of relevant libraries
[pip3] flashinfer-python==0.5.3
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.16.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.3.1
[pip3] nvidia-ml-py==13.580.82
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pytorch-triton==3.5.1+gitbfeb0668
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0.dev20251124+cu128
[pip3] transformers==4.57.3
[pip3] triton==3.5.1
[conda] Could not collect
==============================
vLLM Info
ROCM Version : Could not collect
vLLM Version : 0.11.2.dev420+g62de4f425.d20251201 (git sha: 62de4f425, date: 20251201)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE SYS SYS 0-27,56-83 0 N/A
GPU1 NODE X SYS SYS 0-27,56-83 0 N/A
GPU2 SYS SYS X NODE 28-55,84-111 1 N/A
GPU3 SYS SYS NODE X 28-55,84-111 1 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
==============================
Environment Variables
LD_LIBRARY_PATH=/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.4/lib64:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.8/lib64:/usr/local/cuda-12.4/lib64:/usr/local/cuda-12.4/lib64:
CUDA_HOME=/usr/local/cuda-12.8
CUDA_HOME=/usr/local/cuda-12.8
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_ubuntu
I believe it should be able to run. Are you using a local install/environment for VLLM or the docker version? Tomorrow when I'm doing more quants I can grab a 4x5090 spot instance and see what it does for me. I quantize and test almost all of these on RTX Pro 6000 Blackwell instances.
I am using a local vLLM environment. Can you give me the vllm serve command to launch this model?
I know its not a help, but I couldn't get this NVFP4 running on my 4*5060Ti 16GB setup. I did quantize it to AWQ 4-Bit and that runs, but I'd prefer an NVFP4 version ;)
Can you all try using the official vllm docker container for troubleshooting?
docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model Firworks/GLM-4.5-Air-REAP-82B-A12B-nvfp4 --dtype auto --max-model-len 32768
I just ran that and was able to load it and inference with it on an RTX Pro 6000 Blackwell. You might need to add tensor paralell for the 4x5090/5060ti's.
docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model Firworks/GLM-4.5-Air-REAP-82B-A12B-nvfp4 --dtype auto --max-model-len 32768 --tensor-parallel-size 4
Also for the 5060 the context would probably have to be very short. I'm not exactly sure how it works but I think VLLM can auto size the context for available ram using --gpu-memory-utilization 0.95.
I'll update the model card also. This was run before I was including a sample command on the model cards.