d0281bb526
feat: apply upstream llama.cpp patch to fix Gemma-4 inference issues
2026-04-06 10:25:42 +01:00
bbd8f02014
build: remove -DGGML_CUDA_DISABLE_FUSION=1 from cmake configuration in rocm7-nightlies Dockerfile (this was for a temporary test)
2026-04-03 15:21:58 +01:00
b376d1558b
build: disable GGML CUDA fusion in ROCm build configuration (temporary test)
2026-04-03 15:16:12 +01:00
a7ace8dba7
updted benchmarks
2026-03-30 08:37:15 +01:00
614b00af3e
fixed patch (AI slop!!!)
2026-03-25 09:36:50 +00:00
ca84f4cbf3
patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows
2026-03-25 09:23:19 +00:00
eb03432a50
added router mode section and example models.ini file for use with router mode ( #67 )
2026-03-04 12:09:11 +00:00
5f4698c959
build: Remove amdgpu-unroll-threshold-local CMAKE_HIP_FLAG from ROCm 7 nightlies Dockerfile.
2026-03-03 12:54:45 +00:00
8462d300e7
Update README.md to latest huggingface CLI ( #64 )
...
huggingface-cli changes to hf
HF_TOKEN concerpt intoduced for download speed
2026-03-01 13:49:31 +00:00
a8c3fa89ea
docs: Update Quick Start section with a link to Strix Halo Toolboxes configuration details.
2026-02-22 19:47:30 +00:00
ec245b9b17
feat: Implement OS-aware toolbox command selection (toolbox vs distrobox) in the script and clarify usage in the README.
2026-02-22 19:47:30 +00:00
95aaf23a47
fix: remove trailing backslash ( #60 )
...
* feat: add REPO/BRANCH build args for llama.cpp
- Introduce ARG REPO and ARG BRANCH to replace the hardcoded git clone with: `git clone -b ${BRANCH} --single-branch --recursive ${REPO}` . This allows overriding the llama.cpp repository and branch at build time via `--build-arg`.
- Update `docs/building.md` to recommend using `--build-arg` instead of updating the file
* fix: remove trailing backslash
2026-02-17 21:41:55 +00:00
be936d6b59
feat: add REPO/BRANCH build args for llama.cpp ( #59 )
...
- Introduce ARG REPO and ARG BRANCH to replace the hardcoded git clone with: `git clone -b ${BRANCH} --single-branch --recursive ${REPO}` . This allows overriding the llama.cpp repository and branch at build time via `--build-arg`.
- Update `docs/building.md` to recommend using `--build-arg` instead of updating the file
2026-02-17 19:29:48 +00:00
13a0189b6a
Simplify image cleanup by removing explicit logic for older tagged image versions.
2026-02-14 11:27:59 +00:00
9418384c5f
Updated HF_HUB_ENABLE_HF_TRANSFER to HF_XET_HIGH_PERFORMANCE. ( #56 )
2026-02-09 20:16:21 +00:00
8ff812fbb5
updated benchmarks
2026-02-09 13:30:26 +00:00
632130a2c3
fix: Correct typo in "buy me a coffee" link in README.
2026-02-06 06:53:19 +00:00
033585368c
fix ToC
2026-02-05 19:46:50 +00:00
2d09b9e6db
updated benchmarks
2026-02-05 19:03:13 +00:00
4a97c47c4f
docs: add project context and support sections to README.
2026-02-05 17:53:32 +00:00
f28dee87ef
Update README with correction to model download and inference instructions ( #54 )
...
Updated instructions for downloading model files to include both parts of the example GGUF
2026-02-05 11:21:47 +00:00
eb92804284
feat: move and expand host configuration details with updated kernel parameters and explanations, and add a warning note.
2026-02-04 18:39:07 +00:00
9c6946e4b5
docs: add Table of Contents to README.
2026-02-04 18:34:21 +00:00
616d034bc6
typo
2026-02-04 18:32:24 +00:00
4d09c88011
tidy up README
2026-02-04 18:31:39 +00:00
3684e49a9d
docs: update README to announce the application of a workaround for the ROCm 7 performance regression.
2026-02-04 18:05:10 +00:00
06fc789eba
chore: deprecate and remove ROCm 7.1.1 toolbox and all associated references.
2026-02-04 17:56:41 +00:00
d97efb0cb9
updated gpt-oss benchmakrs to test rocm7 performance patch
2026-02-04 17:46:43 +00:00
785f27b100
MAKE_HIP_FLAGS to fix performance regression
2026-02-04 17:17:51 +00:00
606bc292b9
attempting other ways to apply LLVM patch to rocm7
2026-02-04 16:59:43 +00:00
bd8069fe2f
remove AI slop and use correct envs to pass flasg to HIP compiler
2026-02-04 16:21:32 +00:00
7ffa22d8de
fix: Add temporary workaround for ROCm 7 performance regression by setting HIP_LLVM_FLAGS.
2026-02-04 14:50:32 +00:00
51aab9665d
docs: Add a performance regression warning for Llama.cpp with ROCm 7.1+ or nightly builds.
2026-02-03 10:57:08 +00:00
62904f60dd
update
2026-01-25 09:22:49 +00:00
f5b3a2dfb9
udpated README
2026-01-25 09:22:05 +00:00
353686ac79
moving 6.4.4 toolbox to use official fedora 43 rocm packages that include backported fixes for kernel compatibility
2026-01-24 11:47:35 +00:00
d674531182
added rocm-7.2 benchmarks
2026-01-23 15:11:13 +00:00
9511598be4
added 7.2
2026-01-23 09:19:22 +00:00
0635552fec
updated benchmark scripts
2026-01-23 08:55:25 +00:00
1807e8cff2
Adding ROCm 7.2 backend
2026-01-23 08:07:40 +00:00
ea03c773c6
adding procps-ng to the toolbox runtime
2026-01-15 09:43:05 +00:00
8da5395366
added script to manage cluster
2026-01-14 17:01:00 +00:00
6d70dfc73b
updated with dual-server benchmarks
2026-01-12 13:19:23 +00:00
7268e95b0f
updates
2026-01-12 11:05:31 +00:00
f5b9cd84a2
updated instructions to downgrade kernel
2026-01-11 18:26:26 +00:00
d6c7456bd0
adding system info to benchmark display
2026-01-11 10:04:05 +00:00
259bca04de
small typo fix in 'interactive' word ( #34 )
...
sorry for just 1 letter pull-request, it just bothers me every time I try to find the link to open the benchmark results 🙈
2026-01-11 08:19:16 +00:00
eff3a8ede8
updated downgrade instructions
2026-01-10 11:04:10 +00:00
783998589e
neclean up of legacy toolboxes, removal of rocwmma and renamed rocm7-alpha to rocm-7nightlies. Added new benchmarks
2026-01-10 10:31:04 +00:00
f0e9bc8865
adding warning
2026-01-08 14:47:14 +00:00
Donato Capitella