07d2131d8c
added @64k benchmarks
2026-05-03 16:20:42 +01:00
1bffd6505f
feat: add longctx65536 support to standard and RPC benchmark scripts
2026-05-01 20:19:02 +01:00
d20bb42b04
updated results
2026-04-29 06:45:26 +01:00
73be068e85
feat: upgrade ROCm toolboxes to 7.2.2 and update documentation and CI configurations
2026-04-26 16:25:44 +01:00
1421e87060
feat: add Plausible analytics script to documentation index page
2026-04-21 09:47:16 +01:00
9016c0f8f8
update benchs
2026-04-15 16:54:34 +01:00
66a3314c22
refactor: update MODEL_DIR path to use absolute home directory reference
2026-04-15 11:39:35 +01:00
9707a15df7
feat: add benchmark results for rocm-7_2_1-pr21344 and update results metadata
2026-04-15 11:39:10 +01:00
c2754a810a
fix vulkan builds: add spirv-headers-devel to builder deps
2026-04-15 09:33:13 +01:00
2c2c36d3da
add rocm-7.2.1-pr21344 toolbox (gfx1151 MMQ/MMVQ tile + nwarp tuning)
...
Adds a new toolbox variant based on PR #21344 (pedapudi/llama.cpp@gfx1151-opt)
which tunes MMQ tile sizes (x_max=48, y=64) and warp counts (nwarps=4) for
RDNA3_5 gfx1151, yielding up to +100% prefill throughput at small batch sizes.
Also adds BMI2/FMA/F16C CPU SIMD flags and GGML_CUDA_FA_ALL_QUANTS=ON to match
the benchmark build used in the PR. Wire up CI (build matrix + prune), the
refresh script, and run_benchmarks.sh so results land alongside rocm-7.2.1.
2026-04-15 09:23:58 +01:00
14fae26ad0
add minimax m2.7 benchmarks
2026-04-15 08:09:12 +01:00
4b3c02a405
Update README.md
2026-04-12 21:33:46 +01:00
d74db71362
archvied old multi-node benchmarks
2026-04-11 11:20:30 +01:00
7aa6e6dea9
update benchmarks
2026-04-11 11:18:45 +01:00
a821bcb91d
chore: update rocm-7.2 benchmark configuration to version 7.2.1
2026-04-10 11:48:27 +01:00
c129a04a1c
refactor: remove hblt0 benchmark support and associated comparison scripts
2026-04-10 11:23:06 +01:00
5acf54cd67
fix: Update HuggingFace download commands ( #61 )
2026-04-10 10:56:00 +01:00
1dea385f6a
fix: remove trailing backtick causing syntax error in prune-old-toolboxes workflow
2026-04-09 19:00:44 +01:00
4ac481e7d1
chore: upgrade ROCm version from 7.2 to 7.2.1 across configuration and documentation
2026-04-09 18:33:52 +01:00
d1e49d4aa0
chore: remove llama.cpp PR 21566 patch from rocm7-nightlies Dockerfile
2026-04-07 18:33:18 +01:00
a58d133c5e
chore: update llama.cpp patch to PR 21566 for gemma-4 inference fix
2026-04-07 17:49:16 +01:00
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
Donato Capitella