Comments (2)
Hey @ltm920716, thanks for the report!
I believe this was fixed by the following PR #1986 from @Narsil.
You'll now get this instead:
WARN text_generation_launcher: Could not import Flash Attention enabled models: `USE_FLASH_ATTENTION` is false.
I believe this hasn't been released in a version yet, but you can use the docker image that was released with the commit of the PR above:
ghcr.io/huggingface/text-generation-inference:sha-06edde9
The resulting command would be:
sudo nerdctl run -it --gpus '"device=1"' -e USE_FLASH_ATTENTION=False -p 8080:80 -v /data/models:/data ghcr.io/huggingface/text-generation-inference:sha-06edde9 --model-id /data/Meta-Llama-3-8B-Instruct
from text-generation-inference.
thanks a lot, I will have a try!
from text-generation-inference.
Related Issues (20)
- Disable logging of "grammar" parameter HOT 1
- [BUG] Running FP8 quantized model fails on NVIDIA L4 (repack_fp8_for_marlin) HOT 4
- InternLM2.5 support HOT 1
- Llama3.1-8b with LoRa: This model does not support adapter loading.
- fp8 weight load failed IndexError: list index out of range HOT 2
- Tool call performs worse on v2.2.0 as compared to latest HOT 4
- torch.cuda.OutOfMemoryError: CUDA out of memory. Why isn't it handle by the queue system ?
- Output truncated when max_tokens is None HOT 1
- Release 2.3.0 version HOT 2
- Each process is one gpu HOT 1
- Running FP8 and INT4 on multiple AMDs fails with `torch.cuda.OutOfMemoryError`
- PaliGemma detection task is failing HOT 1
- Allow multi-lora in Messages API HOT 2
- Llama 3.1 8B Instruct failed to start - "< not supported between instances of 'NoneType' and 'int'"
- Resolve lora loading bug
- OpenGVLab/InternVL2-8B model support HOT 1
- If you are interested in multimodal large models, you can join our group
- Generation kwargs assignment when processing a request HOT 2
- Dependencies missing for running quantized Llama models in docker
- How to get the token probability by curl request? HOT 1
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 text-generation-inference.