search

PygmalionAI / aphrodite-engine

Large-scale LLM inference engine
https://aphrodite.pygmalion.chat
GNU Affero General Public License v3.0
1.1k stars 121 forks source link

[Bug]: New Numpy version breaks installation #515

Closed murtaza-nasir closed 2 months ago

murtaza-nasir commented 4 months ago

Your current environment

PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.10 (x86_64)
GCC version: (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0
Clang version: Could not collect
CMake version: version 3.29.5
Libc version: glibc-2.36
Python version: 3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.5.0-35-generic-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 3090
GPU 1: NVIDIA GeForce RTX 3090
GPU 2: NVIDIA GeForce RTX 3090
GPU 3: NVIDIA GeForce RTX 3090

Nvidia driver version: 550.78
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
Address sizes:                      43 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             64
On-line CPU(s) list:                0-63
Vendor ID:                          AuthenticAMD
Model name:                         AMD EPYC 7532 32-Core Processor
CPU family:                         23
Model:                              49
Thread(s) per core:                 2
Core(s) per socket:                 32
Socket(s):                          1
Stepping:                           0
Frequency boost:                    enabled
CPU(s) scaling MHz:                 71%
CPU max MHz:                        2400.0000
CPU min MHz:                        1500.0000
BogoMIPS:                           4799.88
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
Virtualization:                     AMD-V
L1d cache:                          1 MiB (32 instances)
L1i cache:                          1 MiB (32 instances)
L2 cache:                           16 MiB (32 instances)
L3 cache:                           256 MiB (16 instances)
NUMA node(s):                       1
NUMA node0 CPU(s):                  0-63
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Not affected
Vulnerability Retbleed:             Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow: Mitigation; Safe RET
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; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected
Versions of relevant libraries:
[pip3] numpy==2.0.0
[pip3] torch==2.3.0
[pip3] triton==2.3.0
[conda] numpy                     2.0.0                    pypi_0    pypi
[conda] torch                     2.3.0                    pypi_0    pypi
[conda] triton                    2.3.0                    pypi_0    pypiROCM Version: Could not collect
Aphrodite Version: 0.5.3
Aphrodite Build Flags:
CUDA Archs: Not Set; ROCm: Disabled

🐛 Describe the bug

Numpy had a new update today, which means now installing aphrodite via pip or building it from source both result in the following error when trying to run aphrodite after installation:

Traceback (most recent call last):
  File "/home/murtaza/miniconda3/envs/aphrodite/bin/aphrodite", line 5, in <module>
    from aphrodite.endpoints.cli import main
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/endpoints/cli.py", line 3, in <module>
    from aphrodite.endpoints.openai.api_server import run_server
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/endpoints/openai/api_server.py", line 30, in <module>
    from aphrodite.endpoints.openai.serving_chat import OpenAIServingChat
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/endpoints/openai/serving_chat.py", line 23, in <module>
    from aphrodite.modeling.guided_decoding import (
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/modeling/guided_decoding/__init__.py", line 5, in <module>
    from aphrodite.modeling.guided_decoding.lm_format_enforcer_decoding import (
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/modeling/guided_decoding/lm_format_enforcer_decoding.py", line 17, in <module>
    from aphrodite.modeling.guided_decoding.outlines_decoding import \
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/modeling/guided_decoding/outlines_decoding.py", line 17, in <module>
    from aphrodite.modeling.guided_decoding.outlines_logits_processors import (
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/aphrodite/modeling/guided_decoding/outlines_logits_processors.py", line 24, in <module>
    from outlines.fsm.fsm import CFGFSM, RegexFSM
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/__init__.py", line 2, in <module>
    import outlines.generate
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/generate/__init__.py", line 2, in <module>
    from .cfg import cfg
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/generate/cfg.py", line 5, in <module>
    from outlines.models import OpenAI
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/models/__init__.py", line 14, in <module>
    from .openai import OpenAI, azure_openai, openai
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/models/openai.py", line 9, in <module>
    from outlines.base import vectorize
  File "/home/murtaza/miniconda3/envs/aphrodite/lib/python3.11/site-packages/outlines/base.py", line 8, in <module>
    from numpy.lib.function_base import (
ModuleNotFoundError: No module named 'numpy.lib.function_base'
AlpinDale commented 4 months ago

Oh boy. I suppose we have to pin numpy versions too from now on. Thanks for reporting

Does torch not pin numpy already? Weird.

AlpinDale commented 4 months ago

For anyone else who might be running into this issue, please downgrade numpy:

pip install numpy==1.26.4