main to custom gpu kernels branch#174
Closed
sdevinenamd wants to merge 21 commits intocustom-gpu-kernelsfrom
Closed
main to custom gpu kernels branch#174sdevinenamd wants to merge 21 commits intocustom-gpu-kernelsfrom
sdevinenamd wants to merge 21 commits intocustom-gpu-kernelsfrom
Conversation
* initial commit of gaia-agents * Improve GAIA playbook docs and GPU detection * fix npu ready, requires an updated amd-gaia package (>v0.16.1), coming soon. * Version instructions --------- Co-authored-by: Kalin Ovtcharov <kalin@extropolis.ai> Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
* Added tests for Windows, and the Z-Image workflow JSON * Windows Desktop Installer, Linux git * Added comfyui-sync-requirements-windows test * Installing comfyui-frontend-package and verifying installation * Updating models copy into AppData folder * Updating the rocm-smi test for Linux * Updating workflows to python 3.12 * Revert "Updating workflows to python 3.12" This reverts commit 18b5480. * Ensure Python can find ROCm shared libraries * Python 3.12 and pip install requests * Updating all workflows to use Python 3.12 * Update playbooks.json with required_platforms
* Added automated tests for the lmstudio-rocm-llms playbook * LM Studio Model Key updated Updated model key from `openai/gpt-oss-120b` to `gpt-oss-120b`. * Increase max_tokens, reduced code (combined bash and powershell) * Updating model loading and unloading logic * Preventing CI failure even if there is no model to unload * Remove model unloading * Update lmstudio-chat-gpt-oss test * Enable Kracken on Windows and Linux * Removing KRK, adding a test to stop lms server * Enabling Linux Halo * Added model unloading tests, unique model identifier for every load * Update lmstudio.md as on main --------- Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
* minor tips and fixes * minor fix * improving pytorch rocm playbook * small fix for tests * other changes --------- Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
* Add AMD copyright to key files * fix formatting issue * fix formatting issue --------- Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
* refactor shown platforms * rename shown to supported * Add device mapping * minor bug fix
Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
* Differentiate between halo and halo box * device mapping * Progress * good selection
* add llama factory finetuning playbook * update llama factory playbook * update llama factory playbook * correct an typing error * mark pytorch setup as an optional step * add webUI tool info * updated some content * updated * update finetuning time * small updates * remove bitsandbytes and docker setup * add the dependency info * correct typo issue * ui and text formatting * ui * update playbook json file * add supported platforms --------- Co-authored-by: Adam Lam <adamlam2@amd.com> Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.