github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-02-05 03:45:12 -05:00
Code Issues Packages Projects Releases Wiki Activity
2,434 Commits 320 Branches 75 Tags
ea66bf386a50fa031b3fc08eaefea7b9ccd5fe8e
Commit Graph

113 Commits

Author SHA1 Message Date
Peter Park
ea66bf386a Fix more links in documentation (#4551) 
* fix vllm engine args link

* remove RDNA subtree in under system optimization in toc

* fix RDNA 2 architecture PDF link

* fix CLR LICENSE.txt link

* fix rocPyDecode license link
 2025-04-01 15:56:34 -04:00
Peter Park
ac2c5e72d4 Fix links in documentation 2025-04-01 15:39:20 -04:00
Peter Park
424e6148bd Add MaxText training Docker doc 
Add MaxText training Docker doc
 2025-03-28 11:25:06 -04:00
Pratik Basyal
a0faccba37 AMD GPU Docs System optimization migration changes in ROCm Docs Develop (#4538) 
* AMD GPU Docs System optimization migration changes in ROCm Docs (#296)

* System optimization migration changes in ROCm

* Linting issue fixed

* Linking corrected

* Minor change

* Link updated to Instinct.docs.amd.com

* ROCm docs grid updated by removing IOMMU.rst, pcie-atomics, and oversubscription pages

* Files removed and reference fixed

* Reference text updated

* GPU atomics from 6.4.0 removed
 2025-03-27 16:38:10 -04:00
Peter Park
58d42ec50b Improve "tuning guides" landing page (#4504) 
* Improve "tuning guides" landing page

* Update docs/how-to/gpu-performance/mi300x.rst

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

* Update docs/how-to/gpu-performance/mi300x.rst

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

* change tuning to optimization

---------

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
 2025-03-25 13:54:27 -04:00
Peter Park
8f359da39e Update Megatron-LM doc for 25.4 (#4520) 
* update megatron-lm doc

* update 'previous versions'

* add missing space

* update docker pull tag

* Update options and docker pull tag

* Add performance measurements link to megatron-lm doc

* fix previous versions table

* words

* Simplify system validation section

* minor fixes

* fix perv versions tbl
 2025-03-21 16:49:55 -04:00
Peter Park
2fca094531 PyTorch training Docker update 25.4 (#4482) 
* remove orphan tag

* add hugging face PEFT

* update "previous versions"

* data == ultrachat 200k

* fix "llama 2"

* add ultrachat to wordlist

* fix previous versions table

* add performance measurements

* add mi325x

* fix prev version

* change 'validation' to 'testing

* fix dir name

* fix backtick
 2025-03-13 13:40:00 -04:00
Peter Park
9b2ce2b634 Update vLLM performance Docker docs (#4491) 
* add links to performance results

words

* change "performance validation" to "performance testing"

* update vLLM docker 3/11

* add previous versions

add previous versions

* fix llama 3.1 8b model repo name

* words
 2025-03-13 10:04:21 -04:00
Peter Park
29ba151b48 Fix "VGPR" typo in workload tuning guide (#4484) 
* Fix "VGPR" typo in workload tuning guide

* fix wording
 2025-03-12 10:28:35 -04:00
Pratik Basyal
9aad9ce7ef Content for modprobe added to MI300X system optimization (#4434) 
Added content for modprobe
 2025-03-07 14:52:20 -05:00
Peter Park
1fb42c2591 Update LLM inference performance validation on AMD Instinct MI300X guide to filter by desired model (#4424) 
* WIP

(cherry picked from commit a06a5b5b959a9425e7384fb58b88c3716f380e48)

rm unneeded files

(cherry picked from commit f1d0c00056a83299bdea74a43cd17454999cf2d8)

* add sphinxcontrib.datatemplates

(cherry picked from commit d056b93a325d87b81f54f70c6eb4ae78f4fb0bc1)

* add template

(cherry picked from commit 0691d59f0a1efbda7908762b7a906e30a65c0ee1)

fix template

(cherry picked from commit 01e4bea5522aa5deeaade58c105ff850f449df8b)

WIPO

(cherry picked from commit 4d8daf7445e7be92cd9ee1d39dff564bd8de41f4)

WIP

(cherry picked from commit 9eefd1f5833bc4dc8de9d777ff65a5fe5f826dbd)

update models yaml schema

(cherry picked from commit a5f0fc1e6cc51104dc2d42029bfcf3eea276d270)

add model groups functionality

(cherry picked from commit 13f49f96dd3e5a160d37c52e48a4fbcccdcf4f9e)

add selector headings and fix template

(cherry picked from commit 35f7f2314bcf74b4fd0a8ca10aaabf0de7063bb0)

update template

(cherry picked from commit 9e2dcfe0c7f6e7c2c685866ea83375fbacbc5032)

fix

(cherry picked from commit be51e32791550ddc21785effccb889228394b242)

use classes instead of data tags

(cherry picked from commit cd52d68c504f7e7435d156ae70cf4bde1dfe703e)

update template

(cherry picked from commit 9ed89fee6874b39ee3535fbde54a0a59f346ea2b)

clean up extra wip files

(cherry picked from commit a9f965a104baa966c184054638e935b011526278)

update wordlist

(cherry picked from commit f783656814e896aedd21acd1c8c87b4700c14469)

remove unused template

(cherry picked from commit cac894bd9c2b1262c9c006e5fddbcb742dc6d882)

improve script

(cherry picked from commit ca20ffd4922916616e0924d625652a815f27c35f)

fix template

(cherry picked from commit 752c61fda856fd5b244734636c036c8877e823b9)

fix standalone benchmark output path in template

(cherry picked from commit d8c04203b5ec0f6c2e2307f7890304a3dc5687be)

fix toc

(cherry picked from commit 8df42faf53488ef29f5a263d25032f3d35cd58ed)

update script to prevent flash of unstyled content

import a11y

(cherry picked from commit 46c852717f223a1d8744fab035807cebab4c5404)

add tabindex to wordlist

(cherry picked from commit 11492593f9692f5453045e7ec52c8f8ae9624ae9)

text

update script

* remove unused config option

* reorganize assets

* fix linting warning

* move js from data/ to extension/
 2025-02-28 12:39:02 -05:00
Peter Park
1ea1c5c6e0 fix tab sync and nested tab Megatron-LM doc (#4409) 2025-02-21 17:19:48 -05:00
Peter Park
389fa7071b Update docs on Megatron-LM and PyTorch training Dockers (#4407) 
* Update Megatron-LM and PyTorch Training Docker docs

Also restructure TOC

* Apply suggestions from code review

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

update "start training" text

Apply suggestions from code review

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

update conf.py

fix spacing

fix branding issue

add disable numa

reorg

remove extra text
 2025-02-21 13:07:18 -05:00
Peter Park
618b44ed23 add vllm docker to release highlights (#306) 2025-02-13 12:01:08 -05:00
Peter Park
2751a17cf0 Update vLLM benchmarking guide (#4347) 
* update vllm-benchmark

fix hlist overflow

update standalone benchmarking options

update list of models

fix typo and model name

unnecessary duplicate info

update formatting

update vllm benchmark guide

- remove Llama 2 FP8
- add Jais 13B
- update commands

update docker pull tag

update MAD available models

remove extra mad models not relevant to vllm

update PyTorch version

add changelog

add model names to .wordlist.txt

* Update docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst

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

* Update docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst

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

* Update docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst

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

* fix typo

* update link

* fix link text

* change changelog to previous versions

* fix typo

* remove "for"

---------

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>
 2025-02-05 17:18:35 -05:00
Pratik Basyal
f885b5df6e Updated ROCm install on Linux installation method link (#4313) 2025-01-31 16:48:33 -05:00
Jeffrey Novotny
d401b5f152 Add ToC and index links to the AI Developer Tutorials (#4312) 
* Add ToC and index links to the AI Developer Tutorials

* Change link positioning

* Change wording
 2025-01-29 14:43:32 -05:00
Pratik Basyal
353d2fe1c1 2nd POC for How to Use ROCm for AI (#282) (#4299) 
* New TOC for ROCm for AI developed

Co-authored-by: Peter Park <peter.park@amd.com>
 2025-01-27 15:49:21 -05:00
Peter Park
8dd99fe3a4 fix link to llama cookbook (#4269) 2025-01-17 14:53:36 -05:00
Adel Johar
7754fc4b9d Docs: resolve warnings from sphinx build output 2025-01-16 14:36:47 +01:00
Peter Park
d534f755e4 Add metadata to docs (#3688) 
* add missing metadata

add metadata to mi300 arch doc

add metadata to contributing guide

add metadata to mi300x tuning guides

* update meta to yaml frontmatter

* update to md metadata to myst frontmatter

* remove extra file

* fix spelling
 2025-01-14 08:55:45 -05:00
Peter Park
26553d725b Add TensorFlow compatibility docs (#4247) 
* Add Tensorflow

* WIP

* WIP

* minor fmt

* PR feedbacks

* fix missed inconsistent formatting

* WIP

WIP

WIP

WIP

* minor formatting

update tensorflow-rocm docker images to rocm6.3.1

fix urls

* WIP

* fix typo and update wordlist

* fix tables not rendering

* fix table headings

* add period

* update tf dockers

* fix link

* fix link

* wording

* update historical compat

* fix tensile link

---------

Co-authored-by: Mátyás Aradi <matyas@streamhpc.com>
Co-authored-by: Istvan Kiss <neon60@gmail.com>
 2025-01-09 14:24:58 -05:00
Pratik Basyal
8caa54caca HPC application list updated (#4066) 
* PETSc added

* List of HPC applications updated for 6.2.4

* Leo's feedback incorporated

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

* Review feedback incorporated

* vllm removed

---------

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
 2025-01-08 08:35:42 -05:00
Peter Park
ff1393142b Add JAX compatibility doc (#4234) 
* Add JAX compatibility

(cherry picked from commit 99215ab6b4cf6a1209d6c5fc781b5855251dcba5)

* WIP

(cherry picked from commit 54564a85d340b4149ed80a33377cf54c1eb48713)

* Fix docker table

(cherry picked from commit 8115a905764c869b390de2561e5f1356ec7e9743)

* WIP

(cherry picked from commit 45076e1fd20fd2c43f7a0ab6d8d5d246c498d801)

* add minor formatting

(cherry picked from commit c75706841092006c26766611b0407b79a13c7345)

* PR feedbacks

(cherry picked from commit 236b5daae4251c26cd697c6e20d5982771b05754)

* fix inconsistent formatting

(cherry picked from commit 0c6a2e3627f9e6159e3f400ab18769904c18097e)

* Rename file

(cherry picked from commit f17239aa8a9fa1ecdf8dab08c0348dc9216c5311)

* jax_triton supported

(cherry picked from commit fa56d697fbaa44c0c480df71dc236be8584291c0)

* WIP

(cherry picked from commit e8f0c5741fe96bb1e3272365906334d911a9a849)

* WIP

(cherry picked from commit 8ee4f3c62da8e11eea591340dc7c9fc1be8b7035)

* WIP

(cherry picked from commit 58c6bf441054fe3a21ba2d86808279e90de847b7)

* WIP

(cherry picked from commit 368ddf6925215a9bfd75a43c7c33def12238f81d)

* update .wordlist.txt

(cherry picked from commit 78ac332c8d6eba93e2b3e57440da3f60054bbadb)

* update .wordlist.txt

(cherry picked from commit 8d9492399f4b73b0c3c5359684d5b7faa328ba0f)

* Fix typos

(cherry picked from commit 394dede13b6de087237832fe3c693c11da7d733b)

* update jax note

(cherry picked from commit ceacc713c4295f8bbd20fc622579de9053b73337)

* Update docs/compatibility/ml-compatibility/jax-compatibility.rst

(cherry picked from commit b0613e914a2ba639fddea62eb495f97beaa8ba49)

* Update docs/compatibility/ml-compatibility/jax-compatibility.rst

(cherry picked from commit 8aac4344b6fd4120a3b8a31878f5316df99f3f99)

* Add back hipGraph support

(cherry picked from commit 028ddb3535073e0cd668c24614a0a73a491b5948)

* WIP

(cherry picked from commit 2e0ff9c5e3f88ceea6b0ca770bb4edb52ce08a47)

* WIP

(cherry picked from commit 186802585de5b7d58f9ac2a7947a83c037df1617)

* add blurb about docker icon

(cherry picked from commit aef650d4072578f75e7549151613f390f6545ce1)

* update pytorch-compatibility path in conf.py

* words

---------

Co-authored-by: Mátyás Aradi <matyas@streamhpc.com>
Co-authored-by: Istvan Kiss <neon60@gmail.com>
 2025-01-07 09:57:19 -05:00
alexxu-amd
85bd6e98f5 Remove gpu-cluster-networking and 'Using MPI' page due to migration to Instinct Docs (#4201) 
* remove 'Using MPI' and 'gpu-cluster-networking' sections due to migration to dcgpu

* remove gpu-cluster-networking from index page

---------

Co-authored-by: Alex Xu <alex.xu@amd.com>
 2024-12-30 09:39:46 -05:00
Peter Park
f76145c2ad Fix PyTorch Compatibility link and remove incomplete rows (#4195) 
* fix pytorch-compatibility filename

fix links

* remove incomplete rows in pytorch-compatibility

* fix broken refs
 2024-12-24 11:13:54 -05:00
Peter Park
76d6e892bb Add PyTorch compatibility doc (#4193) 
* Add compatibility framework pages

* update formatting

* WIP

* satisfy spellcheck linter

* PR feedbacks

* caps

* remove jax and tensorflow pages

* comment out "?"s

* update wordlist

* fix toc and table

* update toc and deep-learning-rocm.rst

---------

Co-authored-by: Istvan Kiss <neon60@gmail.com>
 2024-12-23 18:06:22 -05:00
Pratik Basyal
33891d6fd0 Bar memory update develop (#4168) 
* Bar Memory page added

* Leo's feedback incorporated

* Spell check fixed

* SME review feedback incorporated

* Feedback updated

* Indentation fixed

---------

Co-authored-by: prbasyal <prbasyal@amd.com>
 2024-12-20 16:05:49 -05:00
Peter Park
f9dbc1f21f add megatron training doc (#4159) 
* add megatron training doc

update toc

add images

update formatting and wording

formatting

update formatting

update conf.py

update formatting

update docker img

tweak formatting

Fix stuff

fix mock-data/data-path

add specific commit hash to checkout

update docker pull tag

fix docker run cmd and examples path

fix docker cmd

* wording

words

words

* improve title
 2024-12-16 13:37:35 -05:00
Peter Park
78f9adc6ec fix rccl hip streams section in workload tuning guide (#4140) 2024-12-09 11:06:12 -05:00
Peter Park
b0722b3228 Add @hongxiayang updates to MI300X workload tuning guide (#4123) 
minor fixes to formatting

fix spelling errors

more spelling

fixes

quantization update

fix format

simplify wording in tunableops and format fix

Apply suggestions from code review

review feedback by Peter

Co-authored-by: Peter Park <peter.park@amd.com>

Apply suggestions from code review

addressing feedback

Co-authored-by: Peter Park <peter.park@amd.com>

Apply suggestions from code review

feedback again

Co-authored-by: Peter Park <peter.park@amd.com>

add hipblaslt yaml file figure

feedback and minor formatting

formatting

update wordlist.txt

remove outdated sentence regarding fsdp and rccl

(cherry picked from commit 87fa9fd83a2e623f6cab4e69d65f49e3db0a45f6)

update wordlist

Co-authored-by: hongxyan <hongxyan@amd.com>
 2024-12-06 12:10:57 -05:00
Sam Wu
f77e2dd7a7 Sync develop branch (#4078) 2024-12-03 15:18:51 -07:00
Istvan Kiss
0f6f4b7d57 Update docs/how-to/programming_guide.rst 
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
 2024-11-07 17:36:38 +01:00
Istvan Kiss
b0629fdd29 Apply suggestions from code review 
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
 2024-11-07 17:36:38 +01:00
randyh62
493cd06641 Update docs/how-to/programming_guide.rst 2024-11-07 17:36:38 +01:00
Istvan Kiss
385dbc30d3 Update docs/how-to/hip_programming_guide.rst 
Co-authored-by: MKKnorr <MKKnorr@web.de>
 2024-11-07 17:36:38 +01:00
Istvan Kiss
6fe63192a9 WIP 2024-11-07 17:36:38 +01:00
randyh62
fb5c08138e Update docs/how-to/hip_programming_guide.rst 
Co-authored-by: MKKnorr <MKKnorr@web.de>
 2024-11-07 17:36:38 +01:00
Istvan Kiss
d41f1362de Apply suggestions from code review 
Co-authored-by: randyh62 <42045079+randyh62@users.noreply.github.com>
 2024-11-07 17:36:38 +01:00
Istvan Kiss
ba3e128246 Increase visibility of programming guide 2024-11-07 17:36:38 +01:00
Peter Park
0fe08d93d7 Update links to vllm perf validation doc (#3971) 
* update links to vllm perf validation doc

* add PagedAttention to wordlist
 2024-10-30 18:24:18 -04:00
Peter Park
f1fb476f6f add suggestions to vllm perf validation doc (#3968) 2024-10-30 14:25:58 -04:00
Peter Park
35b16c1293 add vllm performance validation doc (#3964) 2024-10-30 13:24:11 -04:00
Kent Russell
74333b667d docs: Remove invalid amd_iommu=on parameter 
Per kernel-parameters.txt, there is no "on" option for amd_iommu. While
intel_iommu has it, amd_iommu is automatically on unless specified
otherwise. For more info, see these 2 links:

https://www.kernel.org/doc/Documentation/admin-guide/kernel-parameters.txt
75aa74d52f/drivers/iommu/amd/init.c (L3481)

Signed-off-by: Kent Russell <kent.russell@amd.com>
 2024-10-18 10:44:07 -04:00
Peter Park
b541be7bcb Update bitsandbytes branch in docs (#3898) 2024-10-15 10:47:56 -04:00
Jeffrey Novotny
4efcaad13d Fix Radeon link and point at R6.1.3 as absolute link (#3757) 2024-09-19 15:57:43 -04:00
Peter Park
1a26868cce add missing make command to bitsandbytes install commands (#3722) 2024-09-13 13:21:44 -04:00
Jeffrey Novotny
4992db3e6c Add FBGEMM/FBGEMM_GPU to the Model acceleration libraries page (#3659) 
* Add FBGEMM/FBGEMM_GPU to the Model acceleration libraries page

* Add words to wordlist and fix a typo

* Add new sections for Docker and testing

* Incorporate comments from the external review

* Some minor edits and clarifications

* Incorporate further review coments and fix test section

* Add comment to test section

* Change git clone command for FBGEMM repo

* Change Docker command

* Changes from internal review

* Fix linting issue
 2024-09-09 11:20:50 -04:00
Jeffrey Novotny
23a67a3abf Add introduction and links to the new guide to the vLLM optimized Doc… (#3637) 
* Add introduction and links to the new guide to the vLLM optimized Docker image on AMD Infinity Hub

* Update target link for the Docker vLLM guide

* Change target URL

* Change link target URL again
 2024-09-04 17:07:46 -04:00
Peter Park
bc64c7b425 Fix intersphinx links (#3668) 
* fix links in install.rst

* fix links in sys opt guides
 2024-09-03 12:28:24 -04:00