-
### What is the issue?
I'm trying to get the project to compile on Gentoo but am running into some issues as Gentoo uses different paths.
On Gentoo, rocm libraries get installed into /usr/lib64, h…
-
Compiling ao from source using `pip install git+https://github.com/pytorch/ao.git` results in a very fun throw
```
NotImplementedError: Could not run 'torchao::quant_llm_linear' with arguments from …
-
### Description
Running a simple program with a global reduction causes a segfault.
The MWE
```python
import jax
print("devices:", jax.devices())
print("local:", jax.local_devices())
x=jax.…
-
### 📚 The doc issue
Hi, could you share the GPU Ops lists based on ROCm platform or how can I get that, thank you :)
### Suggest a potential alternative/fix
_No response_
-
### What happened?
installation fails
### What did you expect would happen?
.
### Relevant log output
```shell
Unpacking resources
Unpacking resources
Download Complete
Looking in indexes: htt…
-
### Your question:
I'm interested in distributing packages that use HIP, AMD's framework for GPU compute. It's basically their equivalent of CUDA. There are a couple of packages on conda-forge rela…
-
### Problem Description
Building a C program that includes rdc/rdc.h from ROCm 6.2.1, I'm hitting this error:
```
In file included from conftest.c:28:
/opt/rocm-6.2.1/include/rdc/rdc.h:325:33: e…
-
### Description
I'm trying to build jaxlib-0.4.30 from source on Fedora 40 using ROCm 6.0.2 that comes in their standard repositories.
Fedora dumps all ROCm libraries/headers directly into `/usr`,…
-
### Problem Description
I am investigating usage of instruction v_mfma_f32_16x16x16_f16 and nvidia equivalent warp-level mma (swizzle SRAM memory + ldmatrix registers + mma over registers, for Ampere…
-
I'm confused about the actual origin of the c++ headers for hipcc (I assumed to be our gcc distribution.
Instead it seems to come from a local installation
I'm in
```
[innocent@patatrack03 binar…