Freezing when running two serves in parallel on different GPUs

[horiacristescu]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

Running two servers, each on a separate port, and with CUDA_VISIBLE_DEVICES set to different device - both servers should run independently.

Current Behavior

They freeze, you can still load /docs but any generation request hangs.

Environment and Context

• Physical (or virtual) hardware you are using, e.g. for Linux:

Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 48 bits physical, 48 bits virtual
CPU(s): 256
On-line CPU(s) list: 0-254
Off-line CPU(s) list: 255
Thread(s) per core: 1
Core(s) per socket: 64
Socket(s): 2
NUMA node(s): 2
Vendor ID: AuthenticAMD
CPU family: 25
Model: 1
Model name: AMD EPYC 7763 64-Core Processor
Stepping: 1
Frequency boost: enabled
CPU MHz: 2824.671
CPU max MHz: 2450.0000
CPU min MHz: 1500.0000
BogoMIPS: 4899.89
Virtualization: AMD-V
L1d cache: 2 MiB
L1i cache: 2 MiB
L2 cache: 32 MiB
L3 cache: 256 MiB
NUMA node0 CPU(s): 0-63,128-191
NUMA node1 CPU(s): 64-127,192-254
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: 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; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not af
fected
Vulnerability Srbds: Not affected
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 mmx fxsr sse sse2 h
t syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_ap
icid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsa
ve avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch os
vw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 in
vpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid c
qm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_ll
c cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save ts
c_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif umip pku
ospke vaes vpclmulqdq rdpid overflow_recov succor smca

• Operating System, e.g. for Linux:

Linux gauss 5.4.0-148-generic #165-Ubuntu SMP Tue Apr 18 08:53:12 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux

• SDK version, e.g. for Linux:

python3 --version
Python 3.11.4

$ make --version
GNU Make 4.2.1
Built for x86_64-pc-linux-gnu
Copyright (C) 1988-2016 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

$ g++ --version
g++ --version
g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Copyright (C) 2019 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

Failure Information (for bugs)

Please help provide information about the failure if this is a bug. If it is not a bug, please remove the rest of this template.

Steps to Reproduce

Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.

1. step 1
2. step 2
3. step 3
4. etc.

Note: Many issues seem to be regarding functional or performance issues / differences with llama.cpp. In these cases we need to confirm that you're comparing against the version of llama.cpp that was built with your python package, and which parameters you're passing to the context.

Try the following:

1. git clone https://github.com/abetlen/llama-cpp-python
2. cd llama-cpp-python
3. rm -rf _skbuild/ # delete any old builds
4. python setup.py develop
5. cd ./vendor/llama.cpp
6. Follow llama.cpp's instructions to cmake llama.cpp
7. Run llama.cpp's ./main with the same arguments you previously passed to llama-cpp-python and see if you can reproduce the issue. If you can, log an issue with llama.cpp

Failure Logs

Please include any relevant log snippets or files. If it works under one configuration but not under another, please provide logs for both configurations and their corresponding outputs so it is easy to see where behavior changes.

Also, please try to avoid using screenshots if at all possible. Instead, copy/paste the console output and use Github's markdown to cleanly format your logs for easy readability.

Example environment info:

llama-cpp-python$ git log | head -1
commit 47b0aa6e957b93dbe2c29d53af16fbae2dd628f2

llama-cpp-python$ python3 --version
Python 3.10.10

llama-cpp-python$ pip list | egrep "uvicorn|fastapi|sse-starlette|numpy"
fastapi                  0.95.0
numpy                    1.24.3
sse-starlette            1.3.3
uvicorn                  0.21.1

llama-cpp-python/vendor/llama.cpp$ git log | head -3
commit 66874d4fbcc7866377246efbcee938e8cc9c7d76
Author: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Date:   Thu May 25 20:18:01 2023 -0600

[gjmulder]

I wonder if you try and run two instances of llama.cpp concurrently if you get the same behaviour?