vllm
vllm copied to clipboard
Published
1 week ago
•
vllm-project
vllm-project
[Usage]: ValueError: fp8_e5m2 kv-cache is not supported with fp8 checkpoints.
Your current environment
PyTorch version: 2.4.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Debian GNU/Linux 11 (bullseye) (x86_64)
GCC version: (Debian 10.2.1-6) 10.2.1 20210110
Clang version: Could not collect
CMake version: version 3.30.2
Libc version: glibc-2.31
Python version: 3.11.2 (main, Jul 23 2024, 17:09:09) [GCC 10.2.1 20210110] (64-bit runtime)
Python platform: Linux-5.4.143.bsk.8-amd64-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA L40
GPU 1: NVIDIA L40
GPU 2: NVIDIA L40
GPU 3: NVIDIA L40
GPU 4: NVIDIA L40
GPU 5: NVIDIA L40
GPU 6: NVIDIA L40
GPU 7: NVIDIA L40
Nvidia driver version: Could not collect
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.2.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.2.0
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): 180
On-line CPU(s) list: 0-179
Thread(s) per core: 2
Core(s) per socket: 45
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 143
Model name: Intel(R) Xeon(R) Platinum 8457C
Stepping: 8
CPU MHz: 2599.260
BogoMIPS: 5198.52
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 4.2 MiB
L1i cache: 2.8 MiB
L2 cache: 180 MiB
L3 cache: 195 MiB
NUMA node0 CPU(s): 0-89
NUMA node1 CPU(s): 90-179
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; TSX disabled
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear arch_capabilities
Versions of relevant libraries:
[pip3] byted-torch==2.4.0.post1
[pip3] flashinfer==0.1.6+cu124torch2.4
[pip3] numpy==1.26.3
[pip3] nvidia-cublas-cu12==12.4.2.65
[pip3] nvidia-cuda-cupti-cu12==12.4.99
[pip3] nvidia-cuda-nvrtc-cu12==12.4.99
[pip3] nvidia-cuda-runtime-cu12==12.4.99
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.0.44
[pip3] nvidia-curand-cu12==10.3.5.119
[pip3] nvidia-cusolver-cu12==11.6.0.99
[pip3] nvidia-cusparse-cu12==12.3.0.142
[pip3] nvidia-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.4.99
[pip3] nvidia-nvtx-cu12==12.4.99
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0+cu124
[pip3] torchaudio==2.4.0+cu124
[pip3] torchvision==0.19.0+cu124
[pip3] transformers==4.44.2
[pip3] triton==3.0.0
[pip3] zmq==0.0.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.0@cea95dfb941878b3370a7c40ca7ab2d549524445
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE NODE NODE SYS SYS SYS SYS SYS 2-89 0 N/A
GPU1 NODE X NODE NODE SYS SYS SYS SYS SYS 2-89 0 N/A
GPU2 NODE NODE X NODE SYS SYS SYS SYS SYS 2-89 0 N/A
GPU3 NODE NODE NODE X SYS SYS SYS SYS SYS 2-89 0 N/A
GPU4 SYS SYS SYS SYS X NODE NODE NODE SYS 92-177 1 N/A
GPU5 SYS SYS SYS SYS NODE X NODE NODE SYS 92-177 1 N/A
GPU6 SYS SYS SYS SYS NODE NODE X NODE SYS 92-177 1 N/A
GPU7 SYS SYS SYS SYS NODE NODE NODE X SYS 92-177 1 N/A
NIC0 SYS SYS SYS SYS SYS SYS SYS SYS 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
How would you like to use vllm
Error encountered when running the fp8 model of deepseek-v2 using vllm with the following startup script: python3 -m vllm.entrypoints.openai.api_server --model deepseek-fp8-model --served-model-name dsv2 --trust-remote-code --tensor-parallel-size 8 --max-model-len 16384 --port $PORT0 --gpu-memory-utilization 0.98 --enforce-eager --kv-cache-dtype fp8_e5m2 >> deepseekv2.log 2>&1
ValueError: fp8_e5m2 kv-cache is not supported with fp8 checkpoints.
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.
