github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-04-05 03:01:17 -04:00
Code Issues Packages Projects Releases Wiki Activity
2,796 Commits 337 Branches 76 Tags
precision_support_update_base
Commit Graph

2796 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alex Xu
58a62bc00e Merge remote-tracking branch 'external/develop' into sync-develop-from-external 2025-05-21 11:16:31 -04:00
Peter Park
56d258592d Finalize 6.4.1 release notes (#408) 
* update URLs for production

* update historical changelog

* remove deep learning compat section from doc highlights

* update changelog.md

* Update CHANGELOG.md

Co-authored-by: yugang-amd <yugang.wang@amd.com>

* Update CHANGELOG.md

Co-authored-by: yugang-amd <yugang.wang@amd.com>

---------

Co-authored-by: yugang-amd <yugang.wang@amd.com>
 2025-05-21 11:15:44 -04:00
Peter Park
8dc7016405 Add Radeon AI PRO R9700, Radeon RX 9070 XT, RX 9060 XT to gpu-arch-specs (#411) 
* add Radeon AI PRO R7900, Radeon RX 9070 XT, Radeon RX 9060 XT to gpu-arch-specs.rst

* update compat matrices

* fix spacing in historical compat csv file
 2025-05-21 11:04:46 -04:00
alexxu-amd
8686bca1b4 Merge pull request #412 from ROCm/alexxu-amd-patch-1 
Add 6.4.1 to version list
 2025-05-21 11:00:11 -04:00
alexxu-amd
82d15a09f5 Merge branch 'develop' into alexxu-amd-patch-1 2025-05-21 10:58:27 -04:00
Peter Park
42e0c0cfba [6.4.1] Add RDNA4 GPUs to docs (#410) 
* add Radeon AI PRO R9700 SD2.1 known issue

* Add hardware support note for R9700, 9070 XT, 9060 XT

* words

* Add links to new 9000-series GPUs
 2025-05-21 10:27:43 -04:00
alexxu-amd
ddcad120a2 Update versions.md 2025-05-21 09:52:05 -04:00
Peter Park
b8892f2c33 add amd-smi ras --cper known issue (#409) 2025-05-20 16:36:33 -04:00
Peter Park
ab384a1b6e [6.4.1] Add RCCL-UnitTests known issue 2025-05-20 07:56:50 -04:00
Peter Park
27db6ef0b3 add rccl known issue to stack known issues (#404) 
* add rccl known issue to stack known issue

* remove bullet
 2025-05-16 12:32:21 -04:00
Istvan Kiss
707d6c022f Merge pull request #388 from ROCm/rn_precision_sup 
Precision support page update release note revert
 2025-05-16 11:33:07 +02:00
Istvan Kiss
3bafe307bf Page will be not published 2025-05-16 11:29:26 +02:00
Peter Park
ca5d0d0000 [6.4.1] update llvm-project version and add RCCL known issue (#401) 
* update llvm-project version

* add RCCL known issue
 2025-05-15 16:20:59 -04:00
randyh62
e35efbae09 Update RELEASE.md (#402) 
Update Added entry, add Changed and Optimized entries
 2025-05-15 13:14:18 -07:00
Daniel Su
0d7846fbab Ex CI: enable rocPRIM sparse checkout (#4743) 2025-05-15 14:39:28 -04:00
Peter Park
92a9c88fe3 [6.4.1 release notes] Change links to internal for external review (#400) 
* change installer links to internal

* change smi changelog links to internal
 2025-05-15 11:48:13 -04:00
Peter Park
2a3c2fe5aa Update 6.4.1 release notes (#399) 
* remove extra file

* Update wording in RELEASE.md

* Update RELEASE.md

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

* update amdsmi changelog

* install -> installed

t

---------

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
 2025-05-14 15:41:12 -04:00
Daniel Su
156917e15d Ex CI: set absolute cmakeSourceDir paths (#4741) 2025-05-14 11:03:57 -04:00
Daniel Su
d7a9280008 Ex CI: set cmakeSourceDir for all components that set cmakeBuildDir (#4738) 2025-05-13 17:15:54 -04:00
Daniel Su
c1825ba41c Ex CI: skip docker creation on gfx942 (#4735) 2025-05-13 17:05:02 -04:00
Peter Park
0a77e7b3a5 docs: Add system health check doc under ROCm for AI (#4736) 
* add initial draft

* add to toc and install page

* update wording

* improve documentation structure

* resturcture and expand content

* add to training section

* add to conf.py article_pages

* Update docs/how-to/rocm-for-ai/includes/system-health-benchmarks.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

* Update docs/how-to/rocm-for-ai/includes/system-health-benchmarks.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

* update wordlist.txt

* Update docs/how-to/rocm-for-ai/includes/system-health-benchmarks.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

* inference --> AI workloads

* udpate toc

* update article_pages in conf.py

* Update system validation notes in training docs

* fix links in prerequisite-system-validation

* wording

* add note

* consistency

* remove extra files

* fix links

* add links to training index page

---------

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
 2025-05-13 15:54:48 -04:00
Daniel Su
a940f3f090 Ex CI: add sparse option to checkout template (#4701) 
* Ex CI: add sparse option to checkout template

* replace Pipeline.Workspace with Agent.BuildDirectory for consistency
 2025-05-13 14:46:48 -04:00
Daniel Su
95415d5e70 Ex CI: remove firstRenderDeviceAccess demand from all components (#4734) 2025-05-13 13:08:27 -04:00
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
Wei Luo
d1debc7e45 [doc]: Add quark in model-quantization.rst (#374) 
* Add quark in model-quantization.rst

---------

Co-authored-by: Peter Park <peter.park@amd.com>
Co-authored-by: Peter Park <git@peterjunpark.com>
 2025-05-08 14:28:51 +08:00
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
Pratik Basyal
169f3bbe5e 641 Release notes update post RC2 batch1 (#387) 
* Release highlight updated

* TOC updated for internal

* RC3 manifest added

* clarify docker image highlight

* update doc highlights

* RC3 changes added

* RC3 manifest added

* ROCm SMI version update

---------

Co-authored-by: Peter Park <peter.park@amd.com>
 2025-05-06 15:07:54 -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
Pratik Basyal
e28eac2fe1 License typo fixed (#384) 2025-05-02 12:37:08 -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
97ccce10ef Links and refernce text update (#383) 2025-05-01 16:13:39 -04:00
Pratik Basyal
217fb452f8 Initial changes to 6.4.1 RN (#379) 
* Initial changes added

* Changelogs for RCCL, hipblaslt, compute profiler, and systems added

* 6.4.0 GA manifest

* 6.4.1 RC1 manifest

* RC2 Manifest added

* Update RELEASE.md

Add CLR Changelog entry for HIP 6.4.1

* Release highlight added

* AMD SMI changelog added

* ROCr runtime changelog added

* RCCL resolved issue added

* Minor change

* Minor fixes

* Quick changes to version

* Offline installer update

* Istallation udpated

* added rocalution to release notes

* Updated changelogs for components

* Changes to changelog

* Update RELEASE.md

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

* Update RELEASE.md

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

* rocSHMEM related changes added

* Changelog updated with new changes

* Heading level fixed

* AMD SMI version bumped to 25.4.0

* Reordered

* Table zebra pattern updated

* Consolidated updated

* Zebra patter aligned

* Add ROCm SMI changes to 6.4.1

* Update CHANGELOG.md

Co-authored-by: Pratik Basyal <prbasyal@amd.com>

* update doc highlights

* Link to rocSHMEM

* update

* Minor changes

* Changelog feedback updated

---------

Co-authored-by: randyh62 <42045079+randyh62@users.noreply.github.com>
Co-authored-by: spolifroni-amd <sandra.polifroni@amd.com>
Co-authored-by: Peter Park <peter.park@amd.com>
 2025-05-01 13:54:31 -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