github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-02-12 15:34:58 -05:00
Code Issues Packages Projects Releases Wiki Activity

[docs/7.11.0] Add llama.cpp known issue (#5962)

Browse Source
This commit is contained in:
peterjunpark
2026-02-12 14:34:54 -05:00
committed by GitHub
parent 1e3eeeaadb
commit 3b2b27ddc7
1 changed files with 13 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
RELEASE.md
View File

@@ -1729,6 +1729,19 @@ known to be affected. As a workaround, use `-Og` optimization level instead of
llama.cpp builds successfully but might fail at runtime with the error "HIP
kernel mul_mat_q has no device code". This issue is under investigation.
### llama.cpp prompt processing performance regression
llama.cpp experiences reduced prompt processing performance across multiple AMD
GPU architectures. As a workaround, pass the compiler flag `-mllvm
--amdgpu-unroll-threshold-local=600` to `hipcc` or `amdclang` when compiling
llama.cpp:
```bash
hipcc -mllvm --amdgpu-unroll-threshold-local=600 ...
```
This issue will be fixed in a future release.
### PyTorch model training validation issues
The following models failed validation on PyTorch for ROCm 7.11.0 due to