Commit Graph

1267 Commits

Author SHA1 Message Date
Boian Petkantchin
20114deea0 In MiniLM JAX example verify MLIR result against JAX 20230516.730 2023-05-16 09:54:07 -07:00
Boian Petkantchin
9acf519078 Add option to skip venv creation in setup script 2023-05-16 09:54:07 -07:00
Boian Petkantchin
bdf37b5311 If device/backend is unknown pass it to IREE verbatim 2023-05-16 09:54:07 -07:00
powderluv
8ee2ac89f8 Rename sharded_vicuna_fp32_web.py to vicuna_web.py 2023-05-16 09:41:35 -07:00
powderluv
60cb48be2e Rename sharded_vicuna_fp32.py to vicuna.py 2023-05-16 09:40:51 -07:00
powderluv
86a215b063 Delete sharded_vicunia.py 2023-05-16 09:37:39 -07:00
powderluv
d6e3a9a236 Delete standalone_vicuna.py 2023-05-16 09:37:26 -07:00
Chi_Liu
a0097a1ead Add mlir_type for torch_model_list.csv (#1428)
- Enable stablehlo/tosa mlir output for torch model
- Add BERT stablehlo support
20230515.729
2023-05-15 10:23:54 -07:00
Ean Garvey
a9bae00606 Fix vulkan device selection at compile time and adapt to IREE python changes. (#1407)
* Add support for vulkan device selection at compile time.

* Don't convert device ID to int and fix .exe imports
20230514.728 20230513.727
2023-05-12 23:31:50 -07:00
Daniel Garvey
4731c1a835 prevent loading tokenizer on import (#1432)
also adds sentencepiece dep for exe
moved vicuna imports to after an if statement
in general we should avoid importing files that load whole models as
global variables
20230512.725 20230512.724
2023-05-12 19:11:45 -07:00
Ean Garvey
4c07e47e8c Specify a few models for expected failure on CUDA CI. (#1430) 2023-05-12 17:03:37 -05:00
Gaurav Shukla
e0cc2871bb [SD] Yield 2 tokens at a time in vicuna
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230511.723
2023-05-11 23:49:01 +05:30
Gaurav Shukla
649f39408b [SD] Fix vicuna response
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-05-11 18:06:21 +05:30
Gaurav Shukla
c142297d73 [SD] Fix gradio to 3.22.0 version
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com
2023-05-11 18:05:55 +05:30
Gaurav Shukla
9e07360b00 [SD] Standalone vicuna with web
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-05-11 17:23:44 +05:30
Gaurav Shukla
7b74c86e42 [SD] Fix SAMPLE_INPUT_LEN import issue
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-05-11 15:41:43 +05:30
Eliasj42
fa833f8366 fixed spacing issue with chat-bot (#1417)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
20230510.722
2023-05-10 16:07:50 -07:00
Gaurav Shukla
fcb059aa38 [SD] Integrate vicuna in the web (#1410) 2023-05-10 11:30:22 -07:00
PhaneeshB
517c670f82 vicuna chat cli 2023-05-10 22:55:06 +05:30
Eliasj42
59df14f18b added vicuna demo (#1408)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
20230510.721 20230509.720
2023-05-09 21:18:20 -07:00
Ean Garvey
6c95ac0f37 Revert dialect registration in model annotator (#1406)
Matches https://github.com/nod-ai/SHARK-Runtime/pull/58
20230509.719
2023-05-09 11:50:19 -07:00
Daniel Garvey
7a4a51ae73 vulkan vic f16 (#1404)
Co-authored-by: dan <dan@nod-labs.com>
20230508.718
2023-05-08 16:46:53 -07:00
powderluv
d816cc015e Revert "added standalone vicuna script (#1399)" (#1402)
This reverts commit 0e4a8ca240.
20230507.717 20230506.716 20230505.715
2023-05-05 16:08:05 -07:00
Eliasj42
54ce3d48ca added standalone vicuna script (#1401)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
2023-05-05 18:05:52 -05:00
Eliasj42
0e4a8ca240 added standalone vicuna script (#1399)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
2023-05-05 15:46:05 -07:00
Daniel Garvey
6ca1298675 maximizes window size for webview launch (#1394) 20230504.714 2023-05-04 20:43:06 -07:00
jinchen62
bbef7a6464 Redesign model manager webui (#1391) 2023-05-04 20:41:29 -07:00
Ean Garvey
cdf2d61d53 Remove imports from iree.compiler.transforms from model annotator. (#1392) 2023-05-04 20:40:19 -07:00
Ean Garvey
6c14847d1f xfail some large tests on macOS builder and switch to hash updates. (#1341)
* Update test-models.yml

* Disable large tests on macOS builder
2023-05-04 19:47:03 -05:00
Gaurav Shukla
68ecdd2a73 [SD] Add LoRA as experimental tab
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230504.713
2023-05-04 22:30:25 +05:30
Gaurav Shukla
3f4d444d18 [SD] Fix stable LM chatbot
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-05-04 22:30:25 +05:30
m68k-fr
e473d0375b [Web] Models folders cleanup (#1365) 20230503.712 2023-05-03 16:13:20 -05:00
Ean Garvey
e38d96850f Fix input image loading in img2img rest API (#1388) 2023-05-03 15:51:00 -05:00
Gaurav Shukla
fed63dfd4b [SD] Add stableLM chatbot (#1383)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-05-03 15:37:20 -05:00
Boian Petkantchin
eba4d06405 In MiniLM JAX example do not hardcode device (#1385)
* In MiniLM JAX example do not hardcode device

* In MiniLM JAX example don't use bytecode MLIR

---------

Co-authored-by: Boian Petkantchin <boian@nod-labs.com>
2023-05-03 10:34:42 -07:00
Boian Petkantchin
4cfba153d2 Add example JAX MiniLM inference (#1380)
* Do not hardcode the name of the VM module in get_iree_module

* Add example JAX MiniLM inference

---------

Co-authored-by: Boian Petkantchin <boian@nod-labs.com>
20230502.711
2023-05-02 15:03:54 -07:00
jinchen62
307c05f38d Convert original vae to diffusers (#1382) 20230502.710 2023-05-02 01:27:28 -07:00
jinchen62
696df349cb Fix curl issue (#1369) 20230501.709 20230430.708 20230429.707 20230428.706 2023-04-28 09:31:14 -07:00
jinchen62
cb54cb1348 Add model manager tab for SD webui (#1368) 2023-04-28 02:43:40 -07:00
Daniel Garvey
9bdb86637d add tkinter launch for webui (#1364) 20230427.705 2023-04-27 19:17:55 -05:00
jinchen62
fb6f26517f Fix webui note (#1367) 2023-04-27 16:14:43 -07:00
Chi_Liu
aa8ada9da9 Add support for torch to stablehlo and tosa in shark_importer (#1360) 2023-04-27 08:09:45 -07:00
powderluv
1db906a373 Revert "Add model manager tab for webui (#1359)" (#1362)
This reverts commit 9d1d1617d8.
2023-04-26 22:25:26 -07:00
jinchen62
9d1d1617d8 Add model manager tab for webui (#1359) 2023-04-26 13:38:18 -07:00
jinchen62
7112789cb8 Add support of using civitai model download url (#1357) 20230425.703 2023-04-25 23:39:52 -07:00
jinchen62
d6b8be2849 Add drawing canvas for img2img stencil scribble (#1355) 20230425.702 2023-04-25 14:41:01 -07:00
powderluv
822171277c Revert "[SD] Add FastChat as part of SD WebUI (#1349)" (#1350)
This reverts commit a5ae9d9f02.
20230424.701
2023-04-24 15:22:25 -07:00
Abhishek Varma
a5ae9d9f02 [SD] Add FastChat as part of SD WebUI (#1349)
-- This commit includes FastChat as part of SD WebUI.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-04-24 11:12:58 -07:00
powderluv
09e3f63d5b Fix pascal (#1346)
* Add fp32 for upscaler VAE

* Plumb Pascal vulkan support
20230423.700 20230423.699
2023-04-23 20:28:25 -07:00
powderluv
d60a5a9396 Add fp32 for upscaler VAE (#1345) 20230423.698 2023-04-23 15:27:55 -07:00