github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00
Code Issues Packages Projects Releases Wiki Activity
1,575 Commits 66 Branches 705 Tags
20230924.962
Commit Graph

1575 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Nelson Sharpe
6773278ec2 Fix checkpoint_path unexpected argument (#1832) 20230926.964 20230925.963 20230924.962 2023-09-24 14:17:52 -07:00
Abhishek Varma
9a0efffcca [Llama2] Fix wrong Vulkan device ID + Add Vulkan compile flags 
-- This commit fixes the wrong Vulkan device being selected during
   runtime.
-- It also adds couple of IREE compilation flags to target specific
   Vulkan device.
-- It also changes the Vulkan device listing to be more in tune with
   lowering control flow.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230923.961 20230922.960 		2023-09-22 22:24:18 +05:30
gpetters94
61c6f153d9 Switch to keras-nightly to fix a Linux issue (#1835) 20230921.959 2023-09-21 12:33:45 -04:00
Phaneesh Barwaria
effd42e8f5 pin gradio to v3.44.3 2023-09-21 17:33:43 +05:30
Sungsoon Cho
b5fbb1a8a0 Rename the func arg save_json to avoid name collision. (#1837) 
* Rename the func arg save_json to avoid name collision.

* black formatted.
20230920.958 20230919.957 		2023-09-19 17:29:27 -05:00
Quinn Dawkins
ded74d09cd [vicuna.py] Keep past key values on device (#1836) 
The past key values are only used within the models themselves and can
be kept on device. For vulkan int4, this gives 44 tok/s (for the first
prompt) and settles at around 26 tok/s on 7900xtx.
 2023-09-19 18:17:41 -04:00
Boian Petkantchin
79267931c1 Add argument --additional_compile_args (#1119) 
This allows to pass more arguemnts to the IREE compiler
Example:
python my-app.py --additional_compile_args="--mlir-pretty-debuginfo --mlir-timing"

Co-authored-by: Boian Petkantchin <boian@nod-labs.com>
 2023-09-19 11:26:03 -05:00
zjgarvey
9eceba69b7 local_tank_cache included into clear_all (#1833) 20230918.956 2023-09-18 00:27:23 -05:00
Ean Garvey
ca609afb6a Update README.md (#1830) 20230917.955 20230916.954 20230915.953 20230914.951 20230914.950 2023-09-14 10:33:57 -05:00
Gaurav Shukla
11bdce9790 [flags] Fix vulkan runtime flags as vma is dropped from iree (#1831) 2023-09-14 08:58:59 -05:00
Ean Garvey
684943a4a6 (SD) Fix tokenizers imports in pyinstaller builds. (#1828) 
* Fix tokenizers metadata.

* (SD) Disable VAE lowering configs (rdna3) and add versioned tunings.

* Update sd_annotation.py

* (SD) Add cv2 to spec.

* Update stencil pipeline with the new img2img arg.
20230913.949 20230912.948 		2023-09-12 12:23:48 -05:00
PhaneeshB
b817bb8455 add roles for llama2 2023-09-12 10:59:28 +05:30
Ean Garvey
780f520f02 Fix vk.target_env extensions and remove redundant SD imports. (#1826) 
* Remove redundant IREE runtime imports.

* Fix vulkan target env extensions.
20230911.946 		2023-09-11 13:42:52 -05:00
Dom
c61b6f8d65 Code refactoring (#1817) 
* use join

* fix bug

* further code optimizations

---------

Co-authored-by: Daniel Garvey <34486624+dan-garvey@users.noreply.github.com>
 2023-09-11 11:30:56 -05:00
Abhishek Varma
c854208d49 [Llama2] Prefetch llama2 tokenizer configs (#1824) 
-- This commit prefetches llama2 tokenizer configs from shark_tank.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230910.942 20230909.941 20230908.940 		2023-09-08 11:29:54 -07:00
Gaurav Shukla
c5dcfc1f13 [vicuna] Exit when mlir is not present in shark tank (#1825) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-09-08 10:30:29 -07:00
Abhishek Varma
bde63ee8ae Add logging feature in WebUI (#1821) 2023-09-08 05:48:05 -07:00
Vivek Khandelwal
9681d494eb Update decomp list and shark trainer for DLRM 20230907.939 20230907.938 2023-09-06 21:24:50 +05:30
Gaurav Shukla
ede6bf83e2 [vicuna] Disabling the IR generation path 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-09-06 20:13:17 +05:30
Ean Garvey
2c2693fb7d Fix torchvision versioning in Linux importer setup. (#1809) 20230905.935 20230905.934 2023-09-05 12:57:03 -05:00
Vivek Khandelwal
1d31b2b2c6 Fix StableHLO Compilation flag 2023-09-05 21:32:33 +05:30
Gaurav Shukla
d2f64eefa3 [chatbot] Remove few outdated models from list (#1814) 20230904.932 2023-09-04 09:26:32 -07:00
Abhishek Varma
87ae14b6ff [SD] Add sdpfa decomposition + update IREE flag 
-- This commit adds Scaled Dot Product Flash Attention's decomposition
   in shark_importer.
-- It also updates `iree-flow-enable-data-tiling` to `iree-opt-data-tiling`.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230904.931 		2023-09-04 18:03:53 +05:30
Phaneesh Barwaria
1ccafa1fc1 fix llama2-70b rewrite tensor dim 20230903.930 20230903.929 20230902.928 20230901.927 2023-09-01 17:27:06 +05:30
jinchen62
4c3d8a0a7f Enable downloading vmfb/mlir for webui (#1807) 20230831.925 20230831.924 2023-08-31 11:05:47 -07:00
jinchen62
3601dc7c3b Fix llama2 13b combined ir (#1803) 20230830.923 20230829.922 20230829.921 20230828.920 2023-08-28 11:34:44 -07:00
Daniel Garvey
671881cf87 Llama2 70b (#1783) 
* llama2 70b IR gen

* fix IR sec llama2 + debug

* llama270b

---------

Co-authored-by: PhaneeshB <b.phaneesh@gmail.com>
20230827.919 20230826.918 20230826.917 		2023-08-25 23:04:28 -07:00
Gaurav Shukla
4e9be6be59 [chatbot] Add debug as class attribute (#1799) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230825.916 20230825.915 		2023-08-25 21:46:29 -07:00
Ean Garvey
9c8cbaf498 Add support for ROCM (Windows) in Studio + compile utils (#1770) 
* WIP: MSVC ROCM support for SHARK Studio

* Make get_iree_rocm_args platform-agnostic.

* Update stable_args.py

* Update rocm arg handling in SD utils

* Guard quantization imports.

Co-authored-by: jam https://github.com/jammm
20230825.914 		2023-08-25 20:56:05 -07:00
Ean Garvey
9e348a114e Revert changes process_skipfiles.py (#1798) 
Keeps a small typo fix but reverts the rest of changes to this file from 450c231171
 2023-08-25 15:31:49 -07:00
jinchen62
51f90a4d56 Update conversion passes for brevitas quant op (#1795) 2023-08-25 17:28:07 -05:00
Abhishek Varma
310d5d0a49 Fix llama2 13b crashing + add spec file for CLI execution of Llama (#1797) 
* [Llama2] Add a fix for Llama2 13B downloading/crashing

-- This commit fixes downloading/crashing of llama2 13B on wrong
   .mlir file.
-- Also adds support for downloading vmfb from shark_tank in CLI.

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

* [llama2] Add a spec file to run Llama/Vicuna CLI exe

-- This commit adds a spec file to run Llama/Vicuna CLI exe.

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

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230825.913 		2023-08-25 09:36:09 -05:00
Ean Garvey
9697981004 Pipe through a debug option to iree compile utils. (#1796) 
* Update compile_utils.py

* Pipe through a flag to toggle debug options in compile utils.

* Update SharkLLMBase.py
 2023-08-25 07:11:11 -07:00
Ean Garvey
450c231171 Add tokenizers to requirements.txt (#1790) 
* Add tokenizers to requirements and pin version

* Update process_skipfiles.py
20230824.911 		2023-08-24 19:44:04 -05:00
Ean Garvey
07f6f4a2f7 Add a short README for the OPT examples and small tweaks. (#1793) 
* Small changes to OPT example.

* Update opt README.

* Add a few modes to batch script.

* Update README.md
 2023-08-24 17:26:11 -07:00
jinchen62
610813c72f Add iree flag to strip assertions (#1791) 2023-08-24 10:51:19 -07:00
Ean Garvey
8e3860c9e6 Remove flags that are default in upstream IREE (#1785) 
* Remove index bits flags now set by default

* Update shark_studio_imports.py
 2023-08-24 11:57:54 -05:00
xzuyn
e37d6720eb Add Hires Fix (#1787) 
* improper test hiresfix

* add sliders & use `clear_cache`

* add resample choices & fix step adjustment

* add step adjustment to img2img

* add resample options to img2img

* simplify hiresfix
- import `img2img_inf` from `img2img_ui.py` instead of just copying it into `txt2img_ui.py`

* set `hri` to None after using

* add more resample types, and don't show output until hiresfix is done

* cleaner implementation

* ran black

* ran black again with jupyter dependencies
20230824.909 		2023-08-24 09:01:41 -07:00
Vivek Khandelwal
16160d9a7d Fix combine mlir script 2023-08-24 19:10:49 +05:30
Sungsoon Cho
79075a1a07 Opt perf (#1786) 
* Define command line args, model-name, max-seq-len, platform, etc.

* Add usage example.

* Add opt_perf_comparision_batch.py.

* Use shlex instead.
 2023-08-24 08:33:12 -05:00
Abhishek Varma
db990826d3 Add Llama2 13B int4 fp16 support (#1784) 
Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230823.908 		2023-08-23 10:00:32 -07:00
gpetters94
7ee3e4ba5d Add stencil_unet_512 support (#1778) 
This should fix any remaining issues with stencils and long prompts.
20230822.907 		2023-08-22 12:23:46 -04:00
Vivek Khandelwal
05889a8fe1 Add LLaMa2-int4-fp16 support (#1782) 20230822.906 2023-08-22 07:45:50 -07:00
jinchen62
b87efe7686 Fix venv setup for brevitas (#1779) 20230821.905 2023-08-21 11:58:51 -07:00
gpetters94
82b462de3a Fix stencils for long prompts (#1777) 20230820.903 20230820.904 20230819.902 20230819.901 2023-08-19 00:26:51 -07:00
Daniel Garvey
d8f0f7bade replace public with private (#1776) 
unload footguns
20230818.899 		2023-08-18 14:22:46 -07:00
gpetters94
79bd0b84a1 Fix an issue with diffusers>0.19.3 (#1775) 2023-08-18 14:06:06 -04:00
jinchen62
8738571d1e Adapt the change of brevitas custom op name (#1772) 20230818.898 20230817.897 20230817.896 2023-08-17 14:24:43 -07:00
Gaurav Shukla
a4c354ce54 [version] Pin diffusers==0.19.3 
Once the latest works with LORA train, unpin it.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-08-17 21:27:10 +05:30
Gaurav Shukla
cc53efa89f [cli] Fix chatbot cli 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-08-17 21:27:10 +05:30