Commit Graph

226 Commits

Author SHA1 Message Date
Donato Capitella 033585368c fix ToC 2026-02-05 19:46:50 +00:00
Donato Capitella 2d09b9e6db updated benchmarks 2026-02-05 19:03:13 +00:00
Donato Capitella 4a97c47c4f docs: add project context and support sections to README. 2026-02-05 17:53:32 +00:00
dougs 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
Donato Capitella 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
Donato Capitella 9c6946e4b5 docs: add Table of Contents to README. 2026-02-04 18:34:21 +00:00
Donato Capitella 616d034bc6 typo 2026-02-04 18:32:24 +00:00
Donato Capitella 4d09c88011 tidy up README 2026-02-04 18:31:39 +00:00
Donato Capitella 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
Donato Capitella 06fc789eba chore: deprecate and remove ROCm 7.1.1 toolbox and all associated references. 2026-02-04 17:56:41 +00:00
Donato Capitella d97efb0cb9 updated gpt-oss benchmakrs to test rocm7 performance patch 2026-02-04 17:46:43 +00:00
Donato Capitella 785f27b100 MAKE_HIP_FLAGS to fix performance regression 2026-02-04 17:17:51 +00:00
Donato Capitella 606bc292b9 attempting other ways to apply LLVM patch to rocm7 2026-02-04 16:59:43 +00:00
Donato Capitella bd8069fe2f remove AI slop and use correct envs to pass flasg to HIP compiler 2026-02-04 16:21:32 +00:00
Donato Capitella 7ffa22d8de fix: Add temporary workaround for ROCm 7 performance regression by setting HIP_LLVM_FLAGS. 2026-02-04 14:50:32 +00:00
Donato Capitella 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
Donato Capitella 62904f60dd update 2026-01-25 09:22:49 +00:00
Donato Capitella f5b3a2dfb9 udpated README 2026-01-25 09:22:05 +00:00
Donato Capitella 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
Donato Capitella d674531182 added rocm-7.2 benchmarks 2026-01-23 15:11:13 +00:00
Donato Capitella 9511598be4 added 7.2 2026-01-23 09:19:22 +00:00
Donato Capitella 0635552fec updated benchmark scripts 2026-01-23 08:55:25 +00:00
Donato Capitella 1807e8cff2 Adding ROCm 7.2 backend 2026-01-23 08:07:40 +00:00
Donato Capitella ea03c773c6 adding procps-ng to the toolbox runtime 2026-01-15 09:43:05 +00:00
Donato Capitella 8da5395366 added script to manage cluster 2026-01-14 17:01:00 +00:00
Donato Capitella 6d70dfc73b updated with dual-server benchmarks 2026-01-12 13:19:23 +00:00
Donato Capitella 7268e95b0f updates 2026-01-12 11:05:31 +00:00
Donato Capitella f5b9cd84a2 updated instructions to downgrade kernel 2026-01-11 18:26:26 +00:00
Donato Capitella d6c7456bd0 adding system info to benchmark display 2026-01-11 10:04:05 +00:00
Arnav Gupta 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
Donato Capitella eff3a8ede8 updated downgrade instructions 2026-01-10 11:04:10 +00:00
Donato Capitella 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
Donato Capitella f0e9bc8865 adding warning 2026-01-08 14:47:14 +00:00
Donato Capitella 758f7e8b50 Update 2025-12-22 16:35:08 +00:00
Donato Capitella 2c8a1e2eef updated benchmarks 2025-12-21 18:49:08 +00:00
Donato Capitella 9ba6812003 feat: upgrade ROCm to 7.1.1 and update associated tooling and documentation 2025-12-07 09:30:14 +00:00
Donato Capitella 7584a31548 updated Qwen Next Benchmarks 2025-12-05 08:32:58 +00:00
Donato Capitella 62b0e5e173 updated recommendation for unified memory to reserve 4Gb to the base os. 2025-11-30 12:40:05 +00:00
Donato Capitella 7f34f51202 Added Qwen-3-Next benchmarks 2025-11-28 17:50:21 +00:00
Donato Capitella df54882433 remove manual application of RPC performance PR (this is merged into master now) 2025-11-28 14:20:03 +00:00
Donato Capitella cbfa74b25b udpated Ubuntu instructions 2025-11-26 17:12:36 +00:00
Donato Capitella 1b5ced1255 make PR-15405 application explicit in logs 2025-11-25 10:02:32 +00:00
Donato Capitella 5105f6cf10 add flag to remvoe RPC PR (for testing) 2025-11-24 17:16:06 +00:00
Donato Capitella c7f4ffc346 updated rpc benchmakrs with long context 2025-11-19 07:35:56 +00:00
Donato Capitella 1d88fca07d added long context benchmakrs for RPC 2025-11-18 10:43:17 +00:00
Donato Capitella d19875828c add script to compare performance with/without forcing the hipblaslt path 2025-11-18 08:45:25 +00:00
kevinjohncolo f631e45674 Create docker-compose-how-to.md (#28)
* Create docker-compose-how-to.md

Simple how-to on using docker compose instead of toolbox.

* Update docker-compose-how-to.md
2025-11-18 08:43:22 +00:00
Donato Capitella 5001413bcc more typos 2025-11-18 08:40:49 +00:00
Donato Capitella 6dc6423034 typo 2025-11-18 08:35:18 +00:00
Donato Capitella 140ba2d035 Updated README 2025-11-18 08:33:54 +00:00