Istvan Kiss
d1772b9ca3
Fix unsupported section structure on JAX ( #4733 )
2025-05-13 17:39:25 +02:00
Istvan Kiss
f65e1412df
Fix compatibility list ( #4731 )
2025-05-13 16:26:36 +02:00
Istvan Kiss
ea1072b11d
JAX compatibility page upate ( #4727 )
2025-05-08 19:31:13 +02:00
Peter Park
90a651d2b6
Merge pull request #4725 from peterjunpark/docs/quark-model-quantization
...
Add quark in model-quantization.rst
2025-05-08 10:34:39 -04:00
Daniel Su
16978a382b
Ex CI: separate ROCgdb build and test jobs ( #4715 )
2025-05-08 09:57:58 -04:00
Daniel Su
dc23bb09c2
Ex CI: add AOMP to RVS ( #4718 )
2025-05-08 09:57:35 -04:00
Peter Park
bb7af3351a
Fix incorrect throughput benchmark command in inference/vllm-benchmark.rst ( #4723 )
...
* update inference index to include pyt inference
* fix incorrect command in throughput benchmark
* wording
2025-05-08 09:24:51 -04:00
Pratik Basyal
8ef1bb0139
rocSHMEM component added to ROCm 6.4.0 documentation ( #4719 )
...
* rocSHMEM added to ROCm 640
* Space removed
* link fixed
2025-05-07 15:31:38 -04:00
Daniel Su
1610837a95
Ex CI: fix copyHIP incorrectly packaging symlinked files ( #4687 )
2025-05-06 14:56:41 -04:00
Daniel Su
b7ce573c66
Ex CI: disable rocm-examples rocfft_callback test ( #4699 )
2025-05-06 14:55:43 -04:00
Peter Park
186c281aba
fix links in pytorch-inference-benchmark.rst ( #4713 )
2025-05-06 13:34:55 -04:00
Peter Park
d44ea40a0d
Add MPT-30B + LLM Foundry doc ( #4704 )
...
* add mpt-30b doc
* add tunableop note
* update MPT doc
* add section
* update wordlist
* fix flash attention version
* update "applies to"
* address review feedback
* Update docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* Update docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* Update docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* update docker details to pytorch-training-v25.5
* update
---------
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
2025-05-02 12:13:20 -04:00
Pratik Basyal
a7c158a14f
Link updated ( #4706 )
2025-05-01 11:41:02 -04:00
Peter Park
85778177a1
Update vLLM docker pull tag 20250415 in vllm-benchmark.rst ( #4702 )
2025-04-30 16:09:30 -04:00
Daniel Su
28060c104b
Ex CI: MIOpen exclude failing GPU_Conv2dTuningAsm_FP32 test ( #4693 )
2025-04-29 10:13:40 -04:00
Istvan Kiss
84177354de
Pytorch compatibility page update
2025-04-29 14:43:40 +02:00
Peter Park
7458fcb7ab
Update JAX MaxText benchmark doc to v25.5 ( #4695 )
...
* fix shell cmd formatting
* add previous versions section
* update docker details and add llama 3.3
* update missed docker image tags to 25.5
2025-04-28 17:52:53 -04:00
Peter Park
16d6e59003
fix link to pytorch-training v25.4 doc ( #4696 )
2025-04-28 17:52:33 -04:00
Daniel Su
fd9f576b26
Ex CI: add roctracer to rocprof-sys dependencies ( #4694 )
2025-04-28 14:04:15 -04:00
Peter Park
a66bc1d85e
fix link to previous version in vllm-benchmark.rst ( #4689 )
2025-04-24 17:54:04 -04:00
Peter Park
36b6ffaf7c
Add QwQ 32B to vllm-benchmark.rst ( #4685 )
...
* Add Qwen2 MoE 2.7B to vllm-benchmark-models.yaml
* Add QwQ-32B-Preview to vllm-benchmark-models.yaml
* add links to performance results
words
* change "performance validation" to "performance testing"
* remove "-Preview" from QwQ-32B
* move qwen2 MoE after qwen2
* add TunableOp section
* fix formatting
* add link to TunableOp doc
* add tunableop note
* fix vllm-benchmark template
* remove cmdline option for --tunableop on
* update docker details
* remove "training"
* remove qwen2
2025-04-24 16:44:34 -04:00
Peter Park
40e4ba3ecc
Update vLLM inference benchmark Docker guide ( #4653 )
...
* Remove JAIS 13B and 30B
* update Docker details - vLLM 0.8.3
* add previous version
* Update docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst
* fix link to previous version
2025-04-24 15:59:13 -04:00
Peter Park
1f41ce26be
Add note for chai-1 benchmark Docker in pytorch-inference-benchmark.rst ( #4684 )
2025-04-24 15:48:53 -04:00
Daniel Su
9293723381
Ex CI: add targets to rocJPEG artifact names ( #4681 )
2025-04-24 12:13:34 -04:00
Daniel Su
588752ade4
Ex CI: fix rocprofiler-register tests ( #4676 )
2025-04-24 09:52:27 -04:00
Peter Park
c3faa9670b
Add PyTorch inference benchmark Docker guide (+ CLIP and Chai-1) ( #4654 )
...
* update vLLM links in deploy-your-model.rst
* add pytorch inference benchmark doc
* update toc and vLLM title
* remove previous versions
* update
* wording
* fix link and "applies to"
* add pytorch to wordlist
* add tunableop note to clip
* make tunableop note appear to all models
* Update docs/how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* Update docs/how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* Update docs/how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* Update docs/how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
* fix incorrect links
* wording
* fix wrong docker pull tag
---------
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com >
2025-04-23 17:35:52 -04:00
Pratik Basyal
7246a673ce
Broken link fixed ( #4673 )
2025-04-23 13:34:39 -04:00
Pratik Basyal
3f1c07afd7
Known issue for installation failure in 6.4.0 added ( #4666 )
...
* Known issue for installation failure added
* Github issue No. added
* Typo fixed
* Feedback from Anush updated
* Minor change
* Feedback from Fai added
* Public Issue No. updated
* Minor change
2025-04-23 12:26:11 -04:00
Peter Park
b29b3592bd
Update ML framework Docker compatibility docs for 6.4.0 ( #4667 )
...
* update pytorch-compatibility.rst
* update tensorflow compat
fix
* update jax and jax-community docker versions
2025-04-22 16:16:16 -04:00
Daniel Su
2b2732fe6f
Ex CI: add missing packages to rocprof-comp, clean up test job steps ( #4669 )
2025-04-22 15:50:47 -04:00
Daniel Su
396b6375ba
Ex CI: add script to download artifacts from a provided manifest file ( #4662 )
...
* add files
* Allow command line args for download script
* Move script into separate folder
* Add newline to end of script
---------
Co-authored-by: David Dixon <david.dixon@amd.com >
2025-04-22 10:48:41 -04:00
Daniel Su
37a56b4ab6
Ex CI: add double quotes to pip packages with min versions ( #4661 )
2025-04-21 12:03:38 -04:00
Pratik Basyal
fc162d11e0
6.1.5 column added to historical compatibility develop branch ( #4648 )
...
* 6.1.5 column added to historical compatibility
2025-04-17 11:55:32 -04:00
Daniel Su
34288b5af2
Ex CI: add template to create Docker images with docker commit ( #4649 )
2025-04-17 11:01:17 -04:00
Joseph Macaranas
460e4be71d
External CI: rocprofiler-systems CMake flags to find rocjpeg headers ( #4656 )
...
- Also add chrpath dependency
2025-04-17 10:57:41 -04:00
Joseph Macaranas
25ca422954
External CI: MIOpen build fix from aggregate pipeline rebase ( #4651 )
...
Merge conflict resolution dumped the new parameters to the wrong line.
2025-04-17 10:07:33 -04:00
Daniel Su
27edda496d
Ex CI: reenable comgr cache for affected mathlibs ( #4642 )
2025-04-16 15:03:14 -04:00
Peter Park
9ff3c2c885
Update PyTorch training Docker doc for 25.5 ( #4638 )
...
* update pytorch-training to 25.5
* remove llama 2
* Revert "remove llama 2"
This reverts commit dab672fa7bcbd8bff730382c14177df4301a537d.
* add previous version
* fix run cmd
* add link to docker hub
* fix linting issue
* add Llama 3.3 70B
* update
2025-04-15 18:16:22 -04:00
Daniel Su
0d28491d16
Ex CI: make Docker image URLs lowercase ( #4634 )
2025-04-15 16:01:09 -04:00
Peter Park
7f708c8d87
fix links to amdsmi and rocmsmi changelogs ( #4592 )
...
(cherry picked from commit bdcfea9dbd
2025-04-15 15:12:00 -04:00
Daniel Su
2ab35b3732
Ex CI: change Docker containerRegistry to ContainerService3 ( #4631 )
2025-04-15 11:50:34 -04:00
Peter Park
d057d49af1
Fix vllm Dockerfile.rocm path ( #4628 )
2025-04-15 11:26:54 -04:00
Pratik Basyal
15ec4cf910
GitHub link to component in highlights changed to documentation reference in develop ( #4626 )
...
* GitHub link to component in highlights changed to documentation
* Removed entry from ROCm Compute Profiler
* Jeff's feedback added
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
* List updated
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com >
2025-04-15 10:14:58 -04:00
Daniel Su
ec36f39665
Ex CI: fix comparison in aggregatePipeline test condition ( #4622 )
2025-04-14 12:22:29 -04:00
Peter Park
310864e653
fix link to Dockerfile.rocm ( #4573 )
2025-04-14 10:10:03 -04:00
Pratik Basyal
330aa6f23d
640 known issue GitHub link update in develop ( #4617 )
...
* Date updated
* GitHub issue links added
2025-04-11 21:13:10 -04:00
Peter Park
eb090b8788
Fix word ( #4600 )
2025-04-11 18:07:08 -04:00
Pratik Basyal
af18a170bc
Blog link update to 6.4.0 release notes #4596
...
Blog link update to 6.4.0 release notes
2025-04-11 17:48:42 -04:00
Peter Park
8b423430a4
Fix markdownlint errors ( #4597 )
...
* deal with markdownlint errors
* fix mdlint errors in ubuntu24/README.md
2025-04-11 17:32:52 -04:00
Daniel Su
21b22f89f5
Ex CI: update to ROCm 6.4.0 ( #4598 )
2025-04-11 17:32:27 -04:00
