abetlen / abetlen/llama-cpp-python

"split_mode=2 (row)" not working -- got Aborted

Abierto
#1,454 0 comentarios 0 reacciones 0 asignados Ver en GitHub
Lenguaje dominante
Python
Estrellas
10.6k
Forks
1.4k
Métricas de merge de PR
Métricas de PR pendientes

Descripción

# Prerequisites

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

- [Yes] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
- [Yes] I carefully followed the [README.md](https://github.com/abetlen/llama-cpp-python/blob/main/README.md).
- [Yes] I [searched using keywords relevant to my issue](https://docs.github.com/en/issues/tracking-your-work-with-issues/filtering-and-searching-issues-and-pull-requests) to make sure that I am creating a new issue that is not already open (or closed).
- [Yes] I reviewed the [Discussions](https://github.com/abetlen/llama-cpp-python/discussions), and have a new bug or useful enhancement to share.

# Expected Behavior

I am trying to try out 'split-mode = 2' since I found some posts talking about it can boost the inference speed of quantized model. I am running 'mixtral-8x7b-instruct-v0.1.Q6_K.gguf' on a 4-P 40 24GB Linux environment.

# Current Behavior

However, my program got "Aborted" error when I set 'split_mode = 2'. If I set to layer split, it is working as expected.

# Environment and Context

Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.

* 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: 46 bits physical, 48 bits virtual
CPU(s): 24
On-line CPU(s) list: 0-23
Thread(s) per core: 1
Core(s) per socket: 12
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 79
Model name: Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz
Stepping: 1
CPU MHz: 2593.991
BogoMIPS: 5187.98
Hypervisor vendor: Microsoft
Virtualization type: full
L1d cache: 768 KiB
L1i cache: 768 KiB
L2 cache: 6 MiB
L3 cache: 70 MiB
NUMA node0 CPU(s): 0-11
NUMA node1 CPU(s): 12-23
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Mitigation; PTE Inversion
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT Host state unknown
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 cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movb
e popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2
smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt md_clear

* Operating System, e.g. for Linux:

> Linux node-0 5.15.0-1038-azure #45~20.04.1-Ubuntu SMP Tue Apr 25 18:45:15 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux

* SDK version, e.g. for Linux:

```
Python 3.8.17
```

# Failure Information (for bugs)

`llm = Llama(
model_path=args.model_path,
n_ctx=32768,
n_threads=None,
n_gpu_layers=-1,
split_mode=2
)`

![image](https://github.com/abetlen/llama-cpp-python/assets/140116944/ed160160-a0c8-48f4-8793-4c3a2e0166e6)

# Failure Logs

> CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py --grammar_parse_mode json_array --json_keys Name:string,Subtitle:string,Introduction:string
cuda_count: 4
n_gpu_layers: 10

Aborted

Guía de contribución

Abrir la guía de contribución

Evaluación

Este issue todavía no se ha evaluado.

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.