183 Commits

Author SHA1 Message Date
Sam Wu
39891fe185 Sync develop branch 2024-06-04 14:32:36 -06:00
Peter Park
9a347aa168 Update fine-tuning guide: title, improve readibility in code blocks, fix typos (#3222)
* Fix typo

* Add torchtune link

* Add newlines before comments in code blocks for readability

* Update title
2024-06-03 22:11:19 -04:00
Peter Park
fed33835a0 Add "Fine Tuning LLMs" how to guide (#3124)
* Add Fine Tuning LLMs how to guide

* Reorg and refactor Fine-tuning LLMs with ROCm

Update index and headings

Fix formatting and update toc

Split out content from index to overview.rst

Add metadata

Clean up overview

Add inference sections, fix rst errors, clean up single-gpu-fine-tuning

Combine fine-tuning and inference guides

Fix some links and formatting

Update toc and add formatting fixes

Add ck kernel fusion content

Update toc

Clean up model quantization and acceleration

Add CK images

Clean up profiling

Update triton kernel performance optimization

Update llm inference frameworks guide

Disable automatic number of figures and tables in Sphinx conf

Change tabs to spaces

Change heading to end with -ing

Add link fixes and heading updates

Add rocprof/Omniperf/Omnitrace section

Update profiling and debugging guide

Add formatting fixes

Satisfy spellcheck

Fix words

Delete unused file

Finish overview

Clean up first 4 sections

Multi-gpu fine-tuning guide: slight fixes

Update toc

Remove tabs

Formatting fixes

* Minor wording updates

* Add some clean-up

* Update profiling and debugging gudie

* Fix Omnitrace link

* Update ck kernel fusion with latest

* Update CK formatting

* Fix perfetto link syntax

* Fix typos and add blurbs

* Add fixes to Triton optimization doc

* Tabify saving adapters / models section

* Fix linting errors - spellcheck

Fix spelling and grammar

Satisfy linter

Update wording in profiling guide

Add fixes to satisfy linter

More fixes for linting in Triton guide

More linting fixes

Spellcheck in CK guide

* Improve triton guide

Fix linting errors and optics

* Add occupancy / vgpr table

Change some wording

* Re-add tunableop

* Add missing indent in _toc.yml

* Remove ckProfiler references

* Add links to resources

* Add refs in CK optimization guide

* Rename files and fix internal links

* Organize tuning guides

Reorg triton

* Add compute unit diagram

* Remove AutoAWQ

* Add higher res image for Perfetto trace example

* Update link text

* Update fig nums

* Update some formatting

* Update "Inductor"

* Change "Inductor" to TorchInductor

* Add link to official TorchInductor docs
2024-06-03 14:04:33 -04:00
Peter Park
6a5defb825 Add "How to use ROCm for AI" (#3117)
* Add Using ROCm for AI:wq

Add PyTorch Docker installation images

Split doc into subtopics

Add metadata

Clean up index

Clean up hugging face guide

Clean up installation guide

Fix rST formatting

Clean up install and train-a-model

Clean up MAD

Delete unused file

Add ref anchors and clean up MAD doc

Add formatting fixes

Update toc and section index

Format some code blocks

Remove install guide and update toc

Chop installation guide

Clean up deployment and hugging face sections

Change headings to end in -ing

Fix spelling in Training a model

Delete MAD and split out install content

Fix formatting

Change words to satisfy spellcheck linter

* Add review suggestions and add helpful links

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

Add helpful links and add review suggestions

Remove fine-tuning link and links to D5 and MAGMA

Update docs/how-to/rocm-for-ai/deploy-your-model.rst

Co-authored-by: Young Hui - AMD <145490163+yhuiYH@users.noreply.github.com>

Update DeepSpeed link

Add subheading to ML framework installation and closing blurb to hugging face models guide

* Reorder topics
2024-05-30 16:17:44 -04:00
Peter Park
3a68f43df7 Reorg 'Deep learning' and 'Tuning guides' docs (#3153)
* Rename 'Tuning guides' to 'Hardware optimization'

* Move deep learning to Install section

* Change 'Hardware' to 'System' to align with index.md

* Satisfy spellcheck linter

* adding new framework install graphic with JAX

* Fix link to ROCm libraries list

* crop framework_install graphic

* Reset .wordlist.txt update

* Prettify deep learning framework installation page

* Change spacing in list of frameworks

---------

Co-authored-by: Young Hui <young.hui@amd.com>
2024-05-29 14:12:43 -04:00
Peter Jun Park
cf53fda864 Add manual changes to 6.1.2 changelog
Move HIPIFY from 6.1.1.md to 6.1.2.md

Regenerate changelog

Fix accidental autoformat in 6.1.1.md

Update 6.1.2.md and regen changelog

Add AMD SMI for ROCm 6.1.2

Regen changelog

Add rocDecode and update RELEASE.md

Update 6.1.2 intro blurb

Fix arrow symbol

Add (tm) to changelog.jinja template

Incorporate Leo's feedback

Intro blurb wording.
Add missed tested ROCm config (rocDecode)
Add OS support

Add version to release notes h1

Update intro blurb again

Make changelog filepath lowercase

Update blurb

Add extra line to 6.1.2 template

Fix heading in RELEASE

Fix amdsmi changelog link

Remove OS support notice

Add rocDecode to table

Add redecode to CL

Update rocDecode setup script note for clarity

Update AMD SMI changelog

Apply Leo's feedback

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
2024-05-15 13:12:40 -07:00
Bence Parajdi
41da494ef0 fix review comments 2024-05-13 16:26:16 +02:00
Bence Parajdi
7f38465770 add cu setting page 2024-05-13 16:25:31 +02:00
randyh62
7ebd810f7a updates for SWDEV-459863 (#3113) 2024-05-09 12:42:48 -07:00
Sam Wu
f5f2a1f561 Sync develop branch 2024-05-08 15:09:31 -06:00
Peter Jun Park
a5a1e39e61 Fix changelog and release notes
Add \n to top of 6.0.2 template

Update RELEASE.md and 6.1.1.md

Regenerate changelog

Add minor wording changes in RELEASE.md

Incorporate Leo's feedback

Reformat RELEASE.md to fix build issue

Fixes an issue preventing Changelog from appearing in the TOC.

Update AMDSMI link & change 'release highlights' to 'release notes'

Change AMD SMI link from develop to docs/6.1.1
2024-05-08 15:07:00 -06:00
Young Hui - AMD
40615d2950 Add compatibility matrix (#3082)
* add compatibility matrix and custom css

* fix toc

* reorder some components in matrix, add missing tools to reference page

* Update docs/compatibility/compatibility-matrix.rst

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

---------

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
2024-05-06 11:20:35 -04:00
Sam Wu
de6b23da83 Sync develop branches 2024-04-16 15:56:14 -06:00
Lisa Delaney
2ea7ac694e Manually update release notes and changelog
Added known issue for ROCm compiler

https://ontrack-internal.amd.com/browse/SWDEV-454778

Added known issue for RVS

Added known issue for MI200 SRIOV

Updated PEBB test known issue for RVS

Added expansion for PEBB

Added PBQT known issue

expanded P2P Benchmark and Qualification Tool

Edited RVS known issue description based on Leo's input

Added MI300A fixed defect

Removed PEBB and Babel Stream from RVS known issue

Updated RCCL

Added rocm-cmake

Added rocRAND

Added rocWMMA

Added Tensile

Alan's change 1

Alan change to HIPIFY

Alan's edit 3 for MIOpen

OpenMP 2nd bullet fix - Alan edit

Alan's edit - ROCm Compiler

ROCm Validation Suite edits

Alan's edit rocSOLVER

Alan's edit to ROCTracer

Updated hipSPARSELt

Added hipTensor 1.2.0

Added hipTensor

data type correction

updated the RCCL version

Added bullets to known issues for consistency

Changed RAS to Fixed defect
2024-04-16 15:55:29 -06:00
Lisa
a29b54a453 Update links (#2992)
* Update links

* table cleanup

* cross-refs

* wordlist update

* add temp hard links

* verbiage

* docs(index.md): Disable MD051 for Sphinx Markdown anchor point

In general this rule should be followed to avoid broken links

* revert gpu-arch table, remove dropdowns, quick start hyphen removedon index.md

* revise opening text as per PR comment

---------

Co-authored-by: Lisa <lisa.delaney@amd.com>
Co-authored-by: Sam Wu <sam.wu2@amd.com>
Co-authored-by: Young Hui <young.hui@amd.com>
2024-04-12 15:36:23 -04:00
Istvan Kiss
47d06cb492 Precision support (#2815)
* Precision support page initial commit

Move to rst file

Fix details of Mi100

Update docs/about/compatibility/precission-support.md Co-authored-by: MKKnorr <MKKnorr@web.de>

* Update precission-support page

Co-authored-by: MKKnorr <MKKnorr@web.de>

* PR fix based on feedbackcs

* Rename precision-support.rst to data-type_support.rts

* Update rocThrust library data type support

* PR findings fixes

* Update data-type-support page

Co-authored-by: MKKnorr <MKKnorr@web.de>

* Update docs/about/compatibility/data-type-support.rst

Co-authored-by: MKKnorr <MKKnorr@web.de>

* lisa edits

---------

Co-authored-by: MKKnorr <MKKnorr@web.de>
Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
2024-03-05 09:48:14 -07:00
MKKnorr
cd586348f5 Add instinct gpu architectures information (#2859)
* Add instinct gpu architectures information

* Improve gpu architecture table

Move table to "reference" instead of "conceptual"

* Add HIP terminology to GPU Arch glossary
2024-02-29 15:03:23 -07:00
Lisa
371b06f2c0 What is updates (#2923) 2024-02-23 12:13:26 -07:00
Istvan Kiss
67e3fc994b MI300 documentation (#2779)
---------

Co-authored-by: Nagy-Egri Máté Ferenc <mate@streamhpc.com>
Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
Co-authored-by: Davide Teixeira <77169625+daviteix@users.noreply.github.com>
2024-02-20 17:02:36 -07:00
Istvan Kiss
02cc970a75 Update github links to ROCm organization 2024-02-09 17:03:40 +01:00
Lisa
3c94962813 new banner images (#2884) 2024-02-08 11:53:48 -07:00
Lisa
8bbd51376d update contributing section & update card images (#2865) 2024-02-07 09:31:45 -07:00
Sam Wu
d509656c6b Fix typo (#2809) 2024-01-16 10:48:21 -07:00
Lisa
5f9842db8f link fixes & consistency (#2761) 2023-12-20 12:42:15 -07:00
Sam Wu
6c90336e67 Merge docs/6.0.0 into develop (#2756)
* Marking TransferBench as beta (#2727)

* Known issues (#2731) (#2732)

* rearranging

* edits

* update toc

* link update

* line break

* updates

* Update RELEASE.md

* edits

* Update conf.py

* file cleanup

* Update RELEASE.md

* Update conf.py

* addition

* verbiage

* Update CHANGELOG.md

* edits

* edits

* updates

* edits

* more edits

* Update RELEASE.md

Limited OS to start in 6.0

* Update RELEASE.md

* Update RELEASE.md

Table to reflect support.

* Update RELEASE.md

tweaked language

* Update RELEASE.md

Tweaking language

* edits

* edits

* link

* spelling

* add link

* new section

* Add files via upload (#2701)

* updates

---------

Co-authored-by: Lisa <lisa.delaney@amd.com>
Co-authored-by: Saad Rahim (AMD) <44449863+saadrahim@users.noreply.github.com>
Co-authored-by: Ronnie Chatterjee <111161280+ronniec91@users.noreply.github.com>
Co-authored-by: abhimeda <138710508+abhimeda@users.noreply.github.com>

* docs(library-index.md): Add MIVisionX to library index (#2736)

* Delete docs/about/compatibility/linux-support.md (#2734)

* Delete docs/about/compatibility/linux-support.md

* Update _toc.yml.in

* Update _toc.yml.in

---------

Co-authored-by: Sam Wu <sam.wu2@amd.com>

* Corrected OS version (#2738)

* Corrected OS version 

There is no 22.04.5 exist.
It's 22.04.3 which has been tested and supported

* Update CHANGELOG.md

* Update _toc.yml.in (#2750)

---------

Co-authored-by: Saad Rahim (AMD) <44449863+saadrahim@users.noreply.github.com>
Co-authored-by: Lisa <lisa.delaney@amd.com>
Co-authored-by: Ronnie Chatterjee <111161280+ronniec91@users.noreply.github.com>
Co-authored-by: abhimeda <138710508+abhimeda@users.noreply.github.com>
Co-authored-by: pramenku <7664080+pramenku@users.noreply.github.com>
2023-12-19 15:43:04 -07:00
yhuiYH
eeb96ebb18 Move documentation contributing.md and add Governance.md and Contributing.md (#2690)
* moved contributing.md to new location as it describes contributing to documentation

* Adding Governance.md and high-level Contributing.md

* fix linting errors (asterisk, whitespace and unused links)

* More linting fixes

* merge conflicts

* verbiage

* License link moved out of codeblock, and text fix there. Changed to full name of AMD. Update links to ROCm Org path

* whitespace linting fix

* Reverted back to ROCm is lead and managed by AMD.  Flows better to me.

---------

Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
2023-12-15 16:14:13 -07:00
Lisa
a121e35aa7 rearranging (#2718) 2023-12-15 14:03:14 -07:00
Saad Rahim (AMD)
7179884433 Left Navigation further compression for usability (#2677)
* Left Navigation further compression for usability

* Whitespace

* provide feedback
2023-11-30 13:11:17 -07:00
Lisa
3523e9e822 Open MPI updates (#2655) 2023-11-30 09:58:12 -07:00
Saad Rahim (AMD)
c1ee7d32e0 Removing Linux installation related content (#2673)
* Removing Linux installation related content

* TOC updates

* Removing added files

* Line spacing on code block
2023-11-27 14:03:52 -07:00
Lisa
4adaff02a6 Left nav updates (#2647)
* update gpu-enabled-mpi

update the documentation to also include libfabric based network interconnects,
not just UCX.

* add some technical terms to wordlist

* shorten left nav

* grid updates

---------

Co-authored-by: Edgar Gabriel <Edgar.Gabriel@amd.com>
Co-authored-by: Saad Rahim (AMD) <44449863+saadrahim@users.noreply.github.com>
2023-11-24 07:15:10 -07:00
Lisa
33f110e354 update ROCm name (#2660)
* update ROCm name

* update version history page
2023-11-22 10:30:10 -07:00
Lisa Delaney
f0f4fa15b4 merge conflicts & remove linux install 2023-10-25 13:15:47 -06:00
Sam Wu
b0caf52156 Updates for consistency (#2604)
* Update RELEASE.md and 5.7.0.md to match CHANGELOG.md

* Update 5.2.0.md to match CHANGELOG.md

* Copy CHANGELOG into about folder to match RELEASE

To avoid having divergence in relative links between RELEASE and CHANGELOG
2023-10-24 12:57:39 -06:00
Lisa
fd927e514d What-is and TOC clean-up (#2539) 2023-10-16 15:25:00 -06:00
Saad Rahim (AMD)
50ad3847e5 Docker Image Support table updates (#2545) 2023-10-12 14:00:30 -06:00
Lisa
444efec642 Docker support updates (#2541) 2023-10-11 11:35:10 -06:00
Lisa
4b7775d264 move spack & update pytorch (#2532) 2023-10-10 14:51:55 -06:00
Lisa
e87dba01c6 ROCm restructuring (#2521)
Flattened out page structure for improved navigability.
 * Change Table of Contents 
 * Update the install guides for windows and linux
 * Removed extraneous index pages
 * GPU architecture pages duplicate entries removed
 * spack page cleanup

---------

Co-authored-by: Sam Wu <samwu103@amd.com>
Co-authored-by: Saad Rahim (AMD) <44449863+saadrahim@users.noreply.github.com>
2023-10-06 15:42:11 -06:00
Sam Wu
3176676240 Fix _toc.yml.in
move spack to How To section in Table of Contents

remove duplicate entry in Table of Contents
2023-10-04 16:35:40 -06:00
urtiwari
24614972d3 Updated the table contents related to Spack 2023-10-04 22:22:33 +00:00
urtiwari
1e96665c34 Updated the table contents related to Spack 2023-10-04 22:05:27 +00:00
urtiwari
99073fb9fc Updated the table contents related to Spack 2023-10-04 21:09:56 +00:00
Lisa
940d2933ff Link and formatting fixes (#2482) 2023-09-20 09:55:21 -06:00
Lisa
d0d4eed1a6 Update titles to sentence case (#2455) 2023-09-18 12:26:31 -06:00
Lisa
772b51a7d2 Add ROCm A-Z entries to TOC (#2454) 2023-09-18 12:13:56 -06:00
Lisa
7c5976004f ROCm A-Z page & link cleanup (#2450) 2023-09-13 13:00:50 -06:00
Lisa
890c735f53 site restructure phase 1 - file reorganization (#2428) 2023-09-08 10:02:17 -06:00
Sam Wu
6c0419fb0d Add hipSPARSELt and hipTensor to Projects and licenses (#2431)
* add hipsparselt

* add hiptensor to toc and licenses

* alphabetize licenses

* update rocm-docs-core to 0.23.0
2023-09-05 15:57:10 -06:00
srawat
996064950d OpenMP updates (#2404)
* Added deleted sections to openmp.md and other improvements

* Update CONTRIBUTING.md

* Update _toc.yml.in

* OpenMP updates for 5.7

* Update openmp.md

* Update openmp.md

* Update openmp.md

* Update openmp.md

* Update openmp.md

* Update openmp.md

* Update CONTRIBUTING.md

---------

Co-authored-by: Sam Wu <sam.wu2@amd.com>
2023-09-01 17:28:32 -06:00