Comments (4)
This error is caused by out of GPU memory. See our faq https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/FAQ/faq.html#native-api-failed-native-api-returns-5-pi-error-out-of-resources-5-pi-error-out-of-resources
Could you check your Memory Physical Size(output of sudo xpu-smi discovery -d 0
)? See https://dgpu-docs.intel.com/driver/installation.html#xpu-smi-device-information-and-telemetry. We just find one of customer's Flex 140 only has 5GB memory, but it should be 12GB.
from bigdl.
Hi @qiuxin2012 & @rnwang04, from what I understand, the flex 140 has two GPUs per card, with a memory capacity of 12GB (6GB per GPU). See attached for my output of sudo xpu-smi discovery -d 0
. Currently, the inference is only running on GPU device 0.
from bigdl.
In this case, we many need to run the model inference on two cards using TP or PP.
from bigdl.
As flex 140's memory is so limited, you may add cpu_embedding=True
in https://github.com/intel-analytics/BigDL/blob/main/python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama2/generate.py to help save memory of Embedding layer and see whether it works :
model = AutoModelForCausalLM.from_pretrained(model_path,
load_in_4bit=True,
optimize_model=True,
trust_remote_code=True,
use_cache=True,
cpu_embedding=True)
If not, you can try to run the model inference on two cards using TP or PP, related example is here: https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/Deepspeed-AutoTP
from bigdl.
Related Issues (20)
- Ollama Error on MTL-iGPU HOT 1
- Garbage output on serving 4 parallel users. HOT 6
- vllm not support CodeShell model HOT 2
- LLama-33B failure with vLLM 0.5.4 docker on 4 ARC GPU.
- 1xArc encounters OOM when running Qwen2-7B, load_in_bit=sym_int4. HOT 2
- vLLM 0.5.4 failure to start the TP+ PP mode on 8 ARC HOT 2
- IPEX-LLM 运行源2.0 M32量化版失败 on Intel ARC HOT 1
- Intel Arc A770, Ubuntu 24.04: RuntimeError: could not create an engine
- Llama.cpp + Intel Arc A770, RuntimeError: PyTorch is not linked with support for opencl devices HOT 1
- Running vLLM service benchmark(1xARC770) with Qwen1.5-14B-Chat model failed(compression weight:SYM_INT4). HOT 3
- support for Qwen2 MoE HOT 1
- Error connection when testing fastchat case HOT 1
- Why does the introduction page show the model accuracy instead of token prompt and inference speed, and multi-gpu speed?
- (PI_ERROR_BUILD_PROGRAM_FAILURE)Exception caught at file:C:/Users/Administrator/actions-runner/release-cpp-oneapi_2024_2/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml/src/ggml-sycl.cpp, line:3715 HOT 3
- Running llama3.1 in ollama/langchain fails. HOT 1
- undefined symbol: iJIT_NotifyEvent with oneapi 2024.2, but no issue with 2024.0.1 HOT 4
- Running Docker ollama with Igpu keeps failing to generate.
- Issue with Windows Quickstart Guide. HOT 1
- An error occurred while running the qwen2.5:3b model. HOT 1
- cant run ollama using llp-cpp on 12th igpu under linux
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bigdl.