mistralai/Mixtral-8x7B-Instruct-v0.1 更大。你能向我们展示一下不使用 vLLM 加载模型的代码吗？它可能会将许多层加载到你的 RAM 中，而不是你的 GPU。根据这个帖子，如果以 float32 格式加载 Mixtral,需要 174.49 GB。如果你无法获得更大的机器，我建议你使用 AWQ 版本：https://huggingface.co/ybelkada/Mixtral-8x7B-Instruct-v0.1-AWQ

我正在使用H20-GPT的堆栈通过以下代码加载模型：

python generate.py --base_model=mistralai/Mixtral-8x7B-Instruct-v0.1 --pre_load_embedding_model=True --score_model=None --enable_tts=False --enable_stt=False --enable_transcriptions=False --use_gpu_id=False --max_seq_len=4096

你好。抱歉如果我在混淆问题，但我遇到了相同的问题。

我在HPC上运行这个程序，请求190G的内存和2个GPU。然而，我按照下面的配置信息，只得到了2个32Gb的GPU。

环境配置：

Collecting environment information...
PyTorch version: 2.1.2+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Red Hat Enterprise Linux Server release 7.9 (Maipo) (x86_64)
GCC version: (GCC) 4.9.2
Clang version: Could not collect
CMake version: version 3.29.2
Libc version: glibc-2.17

Python version: 3.11.3 (main, Apr 28 2023, 13:12:35) [GCC 4.9.2] (64-bit runtime)
Python platform: Linux-3.10.0-1160.53.1.el7.x86_64-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: 7.5.17
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: Tesla V100-PCIE-32GB
GPU 1: Tesla V100-PCIE-32GB

Nvidia driver version: 535.54.03
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
Byte Order:            Little Endian
CPU(s):                36
On-line CPU(s) list:   0-35
Thread(s) per core:    1
Core(s) per socket:    18
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 85
Model name:            Intel(R) Xeon(R) Gold 6240 CPU @ 2.60GHz
Stepping:              7
CPU MHz:               2600.158
CPU max MHz:           2600.0000
CPU min MHz:           1000.0000
BogoMIPS:              5200.00
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              1024K
L3 cache:              25344K
NUMA node0 CPU(s):     0-17
NUMA node1 CPU(s):     18-35
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 aperfmperf eagerfpu 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 epb cat_l3 cdp_l3 invpcid_single intel_ppin intel_pt 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 mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm arat pln pts pku ospke avx512_vnni md_clear spec_ctrl intel_stibp flush_l1d arch_capabilities

Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] onnxruntime==1.16.3
[pip3] torch==2.1.2
[pip3] triton==2.1.0
[conda] Could not collectROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.4.0.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
�[4mGPU0	GPU1	NIC0	CPU Affinity	NUMA Affinity	GPU NUMA ID�[0m
GPU0	 X 	SYS	SYS	11	0-1		N/A
GPU1	SYS	 X 	SYS	11	0-1		N/A
NIC0	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:

python -m vllm.entrypoints.openai.api_server --model mistralai/Mixtral-8x7B-Instruct-v0.1 --port 8000 --dtype half --enforce-eager --gpu-memory-utilization 0.5 &

我的系统不支持AWQ

poetry run python -m vllm.entrypoints.openai.api_server --model $ MODEL=TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ --port 8000 --dtype half --enforce-eager --gpu-memory-utilization 0.95  --quantization awq

ValueError: The quantization method awq is not supported for the current GPU. Minimum capability: 75. Current capability: 70.

使用Vllm加载部分层并将剩余的存储在系统RAM中是否有方法？