github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-11-14 21:08:04 -06:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8402] Allow building with BLAS/BLIS now that Ollama's runners are not pure native builds of llama.cpp anymore #67454

New Issue
Open
opened 2026-05-04 10:24:43 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 10:24:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @hmartinez82 on GitHub (Jan 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8402

A regression of ~18tks/s to ~8tks/s eval for llama3.2 in a Ryzen Threadripper 1820X.

Up to version v.0.5.1 I was able to build the official llama-server from llama.cpp and use it as part of an Ollama build that skips generation. I'm using AMD's AOCC compiler and AOCL (A BLIS-flavored implementation tunned for AMD cores) on Linux with -march=znver1.

I was building llama-server with (with AOCC and AOCL configured) with:

cmake -G Ninja -B build \
 -DGGML_BLAS=ON \
 -DGGML_BLAS_VENDOR=AOCL_mt \
 -DCMAKE_C_COMPILER=clang \
 -DCMAKE_CXX_COMPILER=clang++ \
 -DGGML_NATIVE=OFF \
 -DLLAMA_BUILD_TESTS:BOOL=0 \
 -DCMAKE_BUILD_TYPE:STRING=Release \
 -DGGML_AVX:BOOL=1 \
 -DGGML_AVX2:BOOL=1 \
 -DGGML_BLAS:BOOL=1  \
 -DGGML_BUILD_EXAMPLES:BOOL=0 \
 -DBUILD_SHARED_LIBS:BOOL=0 \
 -DGGML_NATIVE:BOOL=0 \
 -DGGML_FMA:BOOL=1 \
 -DGGML_F16C:BOOL=1 \ 
 -DGGML_LTO:BOOL=1 \
 -DCMAKE_C_FLAGS:STRING="-march=znver1" \
 -DCMAKE_CXX_FLAGS:STRING="-march=znver1"  \
 -DCMAKE_INSTALL_PREFIX:PATH=/root/llama.cpp/install \
 -DBLAS_INCLUDE_DIRS:PATH=/root/aocl/5.0.0/aocc/include

But now, Ollama doesn't use a pure build of llama.cpp anymore. And to make things worse, it's passing a runner argument that llama-server doesn't accept.

From my understand the runners are now Go applications that link to llama.cpp at build time.

How can I have a custom build of these Go runners that use BLIS and allow me to pass -march=znver1 at build time?

p.s.: I'm not a Go developer :(

Originally created by @hmartinez82 on GitHub (Jan 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8402 _A regression of ~18tks/s to ~8tks/s eval for llama3.2 in a Ryzen Threadripper 1820X._ Up to version `v.0.5.1` I was able to build the official `llama-server` from llama.cpp and use it as part of an Ollama build that skips generation. I'm using AMD's AOCC compiler and AOCL (A BLIS-flavored implementation tunned for AMD cores) on Linux with `-march=znver1`. I was building `llama-server` with (with AOCC and AOCL configured) with: ``` cmake -G Ninja -B build \ -DGGML_BLAS=ON \ -DGGML_BLAS_VENDOR=AOCL_mt \ -DCMAKE_C_COMPILER=clang \ -DCMAKE_CXX_COMPILER=clang++ \ -DGGML_NATIVE=OFF \ -DLLAMA_BUILD_TESTS:BOOL=0 \ -DCMAKE_BUILD_TYPE:STRING=Release \ -DGGML_AVX:BOOL=1 \ -DGGML_AVX2:BOOL=1 \ -DGGML_BLAS:BOOL=1 \ -DGGML_BUILD_EXAMPLES:BOOL=0 \ -DBUILD_SHARED_LIBS:BOOL=0 \ -DGGML_NATIVE:BOOL=0 \ -DGGML_FMA:BOOL=1 \ -DGGML_F16C:BOOL=1 \ -DGGML_LTO:BOOL=1 \ -DCMAKE_C_FLAGS:STRING="-march=znver1" \ -DCMAKE_CXX_FLAGS:STRING="-march=znver1" \ -DCMAKE_INSTALL_PREFIX:PATH=/root/llama.cpp/install \ -DBLAS_INCLUDE_DIRS:PATH=/root/aocl/5.0.0/aocc/include ``` But now, Ollama doesn't use a pure build of llama.cpp anymore. And to make things worse, it's passing a `runner` argument that `llama-server` doesn't accept. From my understand the runners are now Go applications that link to llama.cpp at build time. How can I have a custom build of these Go runners that use BLIS and allow me to pass `-march=znver1` at build time? p.s.: I'm not a Go developer :(
GiteaMirror added the feature request label 2026-05-04 10:24:43 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No labels feature request
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#67454