Comments (3)
awni
commented on September 22, 2024
Can you be more specific with what you mean by jax metal example? Also why do you need double (64-bit) precision?
from mlx-examples.
QuantumJaeYoo
commented on September 22, 2024
I apologize, I had no time to finish the content, so I just added a dot(.)
To be more specific, I want to ask about the mnist example, I saw that both main.py and torch_main.py support metal backends, but jax_main.py doesn't support it. So I tried to install the jax-metal to test it on my end, and I saw that 64-bit is not supported. The reason why we need 64-bit is we are performing scientific codes requiring high-precision.
from mlx-examples.
awni
commented on September 22, 2024
I see, so Jax may not support 64-bit. I would file an issue with Jax about that as we do not have any ties to the Jax Metal back-end.
If you are interested in higher precision in MLX, you can file an issue to the core repo. It's likely not a top priority for us, but may also not be that much work to have decent op coverage since most of our kernels are templated.
from mlx-examples.
Related Issues (20)
- Support for nanogpt (and gpt-j)
- Tokenizer with bos and eos token id sharing and "[WARNING] Example already has an EOS token appended" HOT 3
- install mlx-lm version 0.16.0 : ERROR: Could not find a version that satisfies the requirement mlx-lm==0.16.0 HOT 1
- [Model Request] Support DCLM-7B HOT 2
- rope_scaling errors when loading Llama-3.1-8B-Instruct HOT 11
- Allocation error when running generation script HOT 4
- [FeatureRequest] support FLUX.1 text to image model HOT 6
- [Feature Request] MLX_lm: Store KV cache of computed prompts to disk to avoid re-compute in follow-up runs HOT 1
- ValueError: "DoRALinear does not yet support quantization" after DoRA fine-tuning HOT 1
- Support example for SpeechT5 model?
- Feature Request: Implement Tool Calling for llama-3.1 in MLX-LM HOT 3
- Example of an async data-loader that automatically pre-fetches batches for training HOT 1
- How to use the Apple Neural Engine with MLX? HOT 1
- mlx_lm.fuse raises RuntimeError: std::bad_cast HOT 1
- [FeatureRequest] Support Qwen2-Audio model
- Optimal way of accumulating gradients? HOT 2
- [FeatureRequest] Support for prompt fine-tuning
- MLX_lm：generate() or stream_generate() how to setting system prompt and model config? HOT 2
- Generation fails after quantization for multi-part models HOT 4
- Update whisper/convert.py to save as safetensors instead of npz
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 mlx-examples.