Comments (8)
I still have this problem, even with commit 0ac38d3. Most recently, it happens with
text-generation-lau ncher --model-id facebook/galactica-120b --num-shard 1 --quantize
for me.
@ScientiaEtVeritas if you are using a 4000 series card, try using the NCCL_P2P_DISABLE=1
environment variable. I was able to go further with that. It's a RTX 4000 software bug where it reports P2P as available but it's not on RTX 4000 hardware.
from text-generation-inference.
What commit are you on? It doesn't seem to be the latest one.
from text-generation-inference.
I'm on the latest release at least (v0.3.0, c720555).
from text-generation-inference.
I published a new release. Can you try with this one?
I was unable to reproduce your issue on my end.
from text-generation-inference.
Closing as stale.
from text-generation-inference.
I still have this problem, even with commit 0ac38d3. Most recently, it happens with text-generation-lau ncher --model-id facebook/galactica-120b --num-shard 1 --quantize
for me.
from text-generation-inference.
Same issue here. While it's trying to load the GPU usage is maxed out, but VRAM usage is low (around 1.5GB)
from text-generation-inference.
Yes, if you see that only a fraction of the GPUs have a 100% GPU utilization, but the other ones are idle it is usually a NCCL issue.
from text-generation-inference.
Related Issues (20)
- Error "Failed to buffer the request body: length limit exceeded" when supplying base64 encoded images greater than 1MB in prompt HOT 2
- Request failed during generation: Server error: 'FlashMixtral' object has no attribute 'compiled_model' HOT 3
- Unable to start TGI with llama3-70b HOT 1
- The EETQ quantization model cannot be performed locally
- Take into account num_return_sequences to get multiple outputs
- Add support for Phi-3 Model HOT 4
- Inference error for Mistral7b v-0.2 while deploying in Azure VM
- Frequency penalty corrupting generations HOT 1
- Shared volume using mountpoint-s3, permissions issues HOT 5
- Planned/Potential of significant work
- Suport for InternVL-Chat-V1-5 HOT 1
- Support for ReFT
- Python client: Extra slash in base_uri leads to failures in chat endpoint
- The TGI loading model consumes all available gpus memory
- Process hangs in local run HOT 1
- Out of Memory Errors When Running text-generation-benchmark Despite Compliant Batch Token Limit HOT 3
- TGI crashes with complex json schemas provided as grammar without any information (on debug/trace level) HOT 1
- Canno launch with error exllamav2_kernels not installed. HOT 4
- Failing to start a TGI pod with 2 or more GPUs. Sharding fails.
- Unable to stop TGI after serving models 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.