[Usage]: How to use FP8 or other quantization algorithms for Minicpmv2_6 #7724
Description
Your current environment
# The output of `python collect_env.py`
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: CentOS Linux 7 (Core) (x86_64)
GCC version: (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2)
Clang version: Could not collect
CMake version: version 3.25.0-rc2
Libc version: glibc-2.17
Python version: 3.9.16 (main, Jul 10 2023, 11:13:07) [GCC 8.3.1 20190311 (Red Hat 8.3.1-3)] (64-bit runtime)
Python platform: Linux-4.18.0-147.mt20200626.413.el8_1.x86_64-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA L40
Nvidia driver version: 535.129.03
cuDNN version: Probably one of the following:
/usr/lib64/libcudnn.so.8.9.2
/usr/lib64/libcudnn_adv_infer.so.8.9.2
/usr/lib64/libcudnn_adv_train.so.8.9.2
/usr/lib64/libcudnn_cnn_infer.so.8.9.2
/usr/lib64/libcudnn_cnn_train.so.8.9.2
/usr/lib64/libcudnn_ops_infer.so.8.9.2
/usr/lib64/libcudnn_ops_train.so.8.9.2
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: 0-22
Off-line CPU(s) list: 23-191
Thread(s) per core: 0
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: 4805.30
Virtualization: VT-x
L1d cache: 2.3 MiB
L1i cache: 1.5 MiB
L2 cache: 96 MiB
L3 cache: 97.5 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 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 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 fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm 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 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid cldemote movdiri movdir64b md_clear pconfig flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] mt-tritonclient==1.0.4
[pip3] mypy-extensions==0.4.3
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu11==11.10.3.66
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu11==11.7.99
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu11==11.7.99
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu11==8.5.0.96
[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-dali-cuda110==1.31.0
[pip3] nvidia-ml-py==12.555.43
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.20
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] onnx==1.12.0
[pip3] onnx-graphsurgeon==0.3.12
[pip3] onnxruntime==1.15.1
[pip3] pynvml==11.5.0
[pip3] pyzmq==26.1.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.0
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.0.0
[conda] No relevant packages
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.5.4@e20233d361b4e6a7cb8e37c6d7f85e9900527802
vLLM Build Flags:
CUDA Archs: ; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X SYS SYS SYS SYS PXB PXB SYS SYS N/A
NIC0 SYS X PIX SYS SYS SYS SYS SYS SYS
NIC1 SYS PIX X SYS SYS SYS SYS SYS SYS
NIC2 SYS SYS SYS X PIX SYS SYS SYS SYS
NIC3 SYS SYS SYS PIX X SYS SYS SYS SYS
NIC4 PXB SYS SYS SYS SYS X PIX SYS SYS
NIC5 PXB SYS SYS SYS SYS PIX X SYS SYS
NIC6 SYS SYS SYS SYS SYS SYS SYS X PIX
NIC7 SYS SYS SYS SYS SYS SYS SYS PIX 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_7How would you like to use vllm
I want to run inference of a minicpm-v2_6 with quantization, I don't know how to implement it with vllm.
The demo only uses llm models, not multimodal models. And which quantization algorithm has the greatest throughput improvement?