Comments (3)
You may want to try removing your target
directory or do some form of cargo clean
to trigger a new compilation from scratch (the new cudarc might have picked a different cuda version on your system and you would need to recompile the PTX files).
from candle.
You may want to try removing your
target
directory or do some form ofcargo clean
to trigger a new compilation from scratch (the new cudarc might have picked a different cuda version on your system and you would need to recompile the PTX files).
Cargo clean, deleting lock file, or even making an entirely new cargo project (including deleting rust entirely and reinstalling) don't have any change in outcome for me. Any new candle projects give me the same error.
From the following steps:
rustup self uninstall
yay -Rdd rustup
yay -S rustup
rustup toolchain install nightly
rustup default nightly
cargo clean
rm Cargo.lock
rm -rf target
cargo build
https://www.toptal.com/developers/hastebin
-- Edit:
Seems deleting ~/.nv and the entire ~/.cache does not change anything either, along with the above steps. The quantized example from candle also doesn't run when using a cuda device (same error)
-- Edit 2:
There's also some new metal kernels around the same time specifically dealing with u32_f32 including tests, unsure if these have snuck in for non-metal.
from candle.
Okay! After a few days of troubleshooting I've tracked down the problem. This wasn't clear to me, but the issue was a cuda 12.5 VS my driver supported cuda 12.4 mismatch. Updating to cuda 12.5 compatible drivers fixes this problem. So the issue was really not the PTX version at all, but the cuda minor version mismatch.
from candle.
Related Issues (20)
- candle-flash-attn infinite compile time HOT 1
- Model Context Not Resetting Between Requests Leading to Invalid Responses
- Tensor not dropped after another tensor was assigned to variable in cuda HOT 3
- Mamba model is broken with `f16` precision HOT 1
- Slow YOLOv8 using MKL
- candle examples fail on cuda with CUDA_DEVICE_NO_ERROR. Device caps of 7.5 HOT 2
- Parler TTS support?
- Positional encoding in DINOv2: Case without interpolation
- new model : DINOv2 reg4 with weights from PlantCLEF 2024 HOT 1
- Retrieving softmax_lse in candle-flash-attn HOT 1
- load_image and load_image_and_resize return different permutations
- How to get raw tensor data? HOT 2
- Qwen/Qwen2-7B doesn't work properly in the example qwen
- Gemma 2 support HOT 2
- Add `QTensor::quantize_onto` to remove a redundant dtoh copy?
- some token duplicated in candle-examples trocr
- Change single value of tensor HOT 3
- Indexing the first dim of a 2D tensor with a 1D tensor HOT 2
- How to get all layers attentions?
- Where should we document benchmarks? HOT 2
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 candle.