github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-02-19 11:56:43 -05:00
Code Issues Packages Projects Releases Wiki Activity
1,745 Commits 66 Branches 705 Tags
debug
Commit Graph

1745 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
jinchen62
534de05791 Update precision check for vicuna (#1610) 20230629.794 2023-06-29 16:16:33 -05:00
Daniel Garvey
5779e8c039 int4/int8 vicuna download support (#1609) 
* set task_topology_max_group to cpu_count

by default. Can be overriden with a flag of the same str

* add download for int4/int8 mlir
 2023-06-29 13:35:51 -07:00
Abhishek Varma
d496053590 [SHARK] Add a compile API to use for quick testing of inference (#1606) 20230628.793 2023-06-28 08:40:28 -07:00
gpetters94
6274a813c9 Add unet512 support for the other StableDiffusion pipelines (#1602) 20230627.792 2023-06-27 12:28:57 -07:00
Gaurav Shukla
1d6a1f9f8a [vicuna] Add tokens streaming(step=3) (#1600) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230627.791 		2023-06-27 08:59:27 -07:00
Daniel Garvey
75672c0e28 set task_topology_max_group to cpu_count (#1594) 
by default. Can be overriden with a flag of the same str
20230626.790 		2023-06-26 14:54:06 -07:00
Prashant Kumar
74a7202173 Make the tensors contiguous. 2023-06-26 17:29:54 +05:30
Prashant Kumar
27a08735db Add the shark backend for torch.compile API. (#1596) 2023-06-26 03:53:32 -07:00
Stefan Kapusniak
eaa49cce17 UI/App - Allow text selection (#1593) 
* When run in app mode on windows, allows selection of text from
non-input controls, which is the same behaviour as web mode.
 2023-06-26 02:16:53 -07:00
powderluv
10657d6fb1 Disable upx 20230625.789 20230625.788 2023-06-25 07:28:52 -07:00
Stefan Kapusniak
e3ab844cd1 Fix output gallery for csv format inc. VAE & LoRA (#1591) 20230624.787 2023-06-24 06:20:53 -07:00
powderluv
5ce6001b41 Update stablelm_ui.py to default to fp16 20230623.786 2023-06-23 22:55:47 -07:00
powderluv
501d0ca52e Add sentencepiece to webui for pyinstaller 2023-06-23 22:52:06 -07:00
powderluv
b444528715 Pin torch-mlir for windows too 20230623.785 20230623.784 2023-06-23 19:19:28 -07:00
Ean Garvey
6e6c90f62b Pin torch-mlir and use local-task in OPT. (#1592) 2023-06-23 19:17:05 -07:00
AyaanShah2204
8cdb38496e Final REST API Fixes (#1590) 
* fixed outpaint api and added tests

* fixed text2img api

* more elegant generator to subscriptable conversion

* final fixes
 2023-06-23 16:46:47 -07:00
powderluv
726d73d6ba Revert "[vicuna] Add streaming of tokens (#1587)" (#1588) 
This reverts commit 4d55e51d46.
 2023-06-23 10:29:00 -07:00
Gaurav Shukla
4d55e51d46 [vicuna] Add streaming of tokens (#1587) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-06-23 08:20:46 -07:00
Prashant Kumar
6ef78ee7ba Add cpu compile time flags. (#1585) 2023-06-23 07:23:26 -07:00
jinchen62
4002da7161 Add int4/int8 options to chatbot webui (#1586) 2023-06-23 07:18:34 -07:00
powderluv
ecb5e8e5d8 Update txt2img_ui.py 2023-06-23 06:42:12 -07:00
PhaneeshB
28e0919321 Add AMD cpu device 2023-06-23 18:47:04 +05:30
Daniel Garvey
28f4d44a6b downloader was double downloading (#1580) 20230622.782 2023-06-22 18:30:27 -07:00
AyaanShah2204
97f7e79391 [Blender Integration] Fixed Inpainting REST API (#1577) 
* fixed inpaint api

* added inpainting test

* fixed linter errors

---------

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
20230622.781 		2023-06-22 16:08:26 -07:00
Nelson Sharpe
44a8f2f8db Include VAE & LoRA data into PNG metadata (#1573) 
* include custom lora and vae data in png metadata

* include pycharm settings

* lint with black
 2023-06-22 16:05:54 -07:00
Eliasj42
8822b9acd7 added ability to use config file to shard vicuna (#1565) 
Co-authored-by: Elias Joseph <elias@nod-labs.com>
 2023-06-22 17:40:35 -05:00
Daniel Garvey
0ca3b9fce3 fix some mmap and vicuna bugs (#1576) 2023-06-22 17:39:55 -05:00
Nithin Meganathan
045f2bb147 Add dispatch-level config file generator for manual annotation (#1566) 2023-06-22 15:11:41 -07:00
Prashant Kumar
a811b867b9 Add shark_eager mode. 
-- Eager mode with step by step op compilation and execution.
 2023-06-22 22:59:14 +05:30
Abhishek Varma
cdd505e2dd [SharkInference-SharkRuntime] Adds capability to mmap vmfbs 
-- This commit is based on [VmModule.mmap() API](https://github.com/openxla/iree/pull/14124).
-- It thereby adds capability to mmap vmfbs in SHARK.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-06-22 20:43:40 +05:30
powderluv
1b0f39107c Move torch_mlir import to the top (#1574) 2023-06-21 22:31:35 -07:00
powderluv
b9b8955f74 exclude vulkan on macos 2023-06-21 22:22:27 -07:00
powderluv
6f7a85eee3 switch to metal backend for CI 2023-06-21 22:17:11 -07:00
Ranvir Singh Virk
18c8e9e51e Metal typo fix (#1572) 
* fixing typos for metal changes

* black formating
20230621.780 		2023-06-21 21:56:11 -07:00
Daniel Garvey
a202bb466a fp16 fixes for webui (#1571) 2023-06-21 20:24:02 -07:00
Ranvir Singh Virk
07c1e1d712 Adding metal_utils for iree_utils (#1561) 
* Adding metal_utils for iree_utils

* Add patch for making compile API work for both MEGABYTE and MiniGPT4 (#1559)

-- It also modifies the mega_test.py script

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

* [SD] Update unet in_channels API and add PIL metadata to spec. (#1560)

* Fix deprecation warning for unet config.

* Include PIL metadata instead of hidden imports in SD spec.

* Fixing iree-metal-target-platform

* adding metal to txt2img pipeline

* Fixing Copyright date

* removing debug prints

* black lint formating

* fixing device dump

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <avarma094@gmail.com>
Co-authored-by: Ean Garvey <87458719+monorimet@users.noreply.github.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
 2023-06-21 19:09:03 -07:00
Ranvir Singh Virk
18daec78c8 Added check for python version (#1570) 
* Added check for python version

* Update for PYTHON_VERSION_X_Y
 2023-06-21 18:56:47 -07:00
Ean Garvey
1a8e2024d6 Exclude non-square sizes from use_tuned on rdna2 (#1568) 2023-06-21 11:36:55 -05:00
AyaanShah2204
d61b6641fb Rest API: Resolved Generator Object not Subscripatable error (#1556) 20230620.779 2023-06-20 19:27:41 -07:00
Phaneesh Barwaria
88cc2423cc Enable Vicuna fp16 cpu (#1562) 
* fix second vic mlir gen

* fp16 mlir/vmfb download from shark_tank
 2023-06-20 13:43:21 -05:00
Ean Garvey
ccf944c1bd Enable tuner for upscaler unet. (#1563) 2023-06-20 13:40:13 -05:00
Ean Garvey
0def74f520 [SD] Update unet in_channels API and add PIL metadata to spec. (#1560) 
* Fix deprecation warning for unet config.

* Include PIL metadata instead of hidden imports in SD spec.
 2023-06-20 10:26:36 -07:00
Abhishek Varma
3fb72e192e Add patch for making compile API work for both MEGABYTE and MiniGPT4 (#1559) 
-- It also modifies the mega_test.py script

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-06-20 10:04:17 -07:00
Vivek Khandelwal
855435ee24 Fix for the user input for Falcon pipeline 2023-06-20 18:09:32 +05:30
Elias Joseph
6f9f868fc0 fixed a bug where designating device for vicuna didn't work 2023-06-20 17:09:32 +05:30
powderluv
fb865f1b99 Move to checkout@v3 
This will break Windows again but we have to fix it up since the old node.js is now deprecated.
20230619.777 		2023-06-19 18:44:36 -07:00
rprasad2
3e5c50f07b changes for tuning (#1542) 
* Add tuning sizes for rdna3
 2023-06-19 15:29:08 -05:00
powderluv
a544f30a8f Move mega to the shark examples (#1555) 2023-06-19 11:10:51 -07:00
Abhishek Varma
1fe56d460a [MEGABYTE] Add script to compile MEGABYTE through SHARK (#1553) 
-- Usage: `python mega_test.py`.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-06-19 11:00:35 -07:00
Vivek Khandelwal
fafd713141 Minor change to falcon pipeline 2023-06-19 22:36:32 +05:30