Commit Graph

1477 Commits

Author SHA1 Message Date
Elias Joseph
16daba99fe wip script for lowering dlrm training 2023-09-06 03:48:20 +00:00
Vivek Khandelwal
98fb6c52df Expand pipelines to fix streaming of tokens 20230731.844 2023-07-31 22:11:01 +05:30
Stefan Kapusniak
206c1b70f4 UI/Web: Reorder tabs to separate SD and LLM (#1701)
Shuffle the tabs around so that:

* All the SD tabs are together
* All the LLM tabs are together
* All the experimental tabs are together
20230730.843 20230729.842
2023-07-29 22:25:30 -04:00
PhaneeshB
cdb037ee54 use shark_args for vulkan debug utils flag 2023-07-30 07:54:26 +05:30
PhaneeshB
ce2fd84538 fix cpu device name for SharkStudio 2023-07-30 07:54:26 +05:30
PhaneeshB
4684afad34 update upscalar example 20230728.841 2023-07-28 21:06:28 +05:30
PhaneeshB
8d65456b7a Move vulkan runtime flags to shark_args 2023-07-28 21:06:28 +05:30
PhaneeshB
d6759a852b add vulkan vma alloc flag 2023-07-28 21:06:28 +05:30
Daniel Garvey
ab57af43c1 Couple of fixes for vicuna.py (#1696)
* mega vicuna merge pt 2

* add fallback to ensure compile is called
20230727.840
2023-07-27 15:53:05 -07:00
jinchen62
4d5c55dd9f Fix vicuna script (#1697) 2023-07-27 17:24:26 -05:00
Vivek Khandelwal
07399ad65c [Langchain] Remove unused code (#1698) 2023-07-27 11:59:54 -05:00
Vivek Khandelwal
776a9c2293 Fix for Langchain (#1694)
For CPU, remove max time stopping criteria
Fix web UI issue
20230726.839
2023-07-26 09:00:23 -07:00
Eliasj42
9d399eb988 fixed bug where device_idx was hardcoded (#1693)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
20230725.838
2023-07-25 19:00:13 -05:00
Vivek Khandelwal
927b662aa7 Add Langchain SHARK Compilation support for all paths 2023-07-25 22:15:42 +05:30
Abhishek Varma
47f8a79c75 [MiniGPT4] Add MiniGPT4 to SHARK (#1554)
* [MiniGPT4] Add MiniGPT4 to SHARK

-- This is the first installment of MiniGPT4 in SHARK.

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

* Add int8 support for MiniGPT4

-- This commit adds int8 support for MiniGPT4.

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

* Update .spec for MiniGPT4's config files

* black format MiniGPT4

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Signed-off-by: Abhishek Varma <abhishek@nod-lab.com>
2023-07-25 09:42:27 -07:00
Stefan Kapusniak
289f983f41 SD - Implement seed arrays for batch runs (#1690)
* SD Scripts and UI tabs that support batch_count can now take a
string containing a JSON array, or a list of integers, as their seed
input.
* Each batch in a run will now take the seed specified at the
corresponding array index if one exists. If there is no seed at
that index, the seed value will be treated as -1 and a random
seed will be assigned at that position. If an integer rather than
a list or json array has been, everything works as before.
* UI seed input controls are now Textboxes with info lines about
the seed formats allowed.
* UI error handling updated to be more helpful if the seed input is
invalid.
20230725.837
2023-07-24 19:22:34 -07:00
Daniel Garvey
453e46562f mega vicuna merge pt 2 (#1685) 2023-07-24 12:42:20 -05:00
Gaurav Shukla
5497af1f56 [config] Add support for uploading sharding config file in chatbot (#1689)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-07-24 10:18:03 -07:00
Vivek Khandelwal
f3cb63fc9c Fix Langchain multiple device isssue (#1688) 2023-07-24 08:03:46 -07:00
Vivek Khandelwal
d7092aafaa Fix multiple issue for Langchain
This commit fixes the following issue for the Langchain:
1.) Web UI not able to fetch results.
2.) For each query model getting reloaded.
3.) SHARK module not using user provided device and precision.
4.) Create a class for main Langchain code.
5.) Misc issues
20230723.835 20230722.834 20230721.833
2023-07-21 21:56:27 +05:30
Vivek Khandelwal
a415f3f70e Fix Langchain Prompt issue and add web UI support (#1682) 2023-07-21 06:36:55 -07:00
Vivek Khandelwal
c292e5c9d7 Add Langchain CPU support and update requirements 20230720.832 20230720.831 2023-07-20 18:53:34 +05:30
Vivek Khandelwal
03c4d9e171 Add support for Llama-2-70b for web and cli, and for hf_auth_token 2023-07-20 14:57:48 +05:30
jinchen62
3662224c04 Update brevitas requirement (#1677)
also clean up useless args

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
20230720.830
2023-07-19 22:03:32 -07:00
Vivek Khandelwal
db3f222933 Revert "Add Llama2 70B option in CLI and WebUI (#1673)" (#1679)
This reverts commit 41e5088908.
2023-07-19 22:02:48 -07:00
Stefan Kapusniak
68b3021325 Fixes cosmetic problems with Gradio 3.37.0 (#1676)
* Fix nod-ai logo having a white border
* Fix control labels having a black background
* Remove extra lower border below Save Prompt checkboxes in Txt2Img UI
2023-07-19 17:28:53 -07:00
AyaanShah2204
336469154d added copy-metadata for pyyaml (#1678) 2023-07-19 17:27:25 -07:00
Abhishek Varma
41e5088908 Add Llama2 70B option in CLI and WebUI (#1673) 2023-07-19 10:41:42 -07:00
PhaneeshB
0a8f7673f4 Add README for CodeGen server 2023-07-19 23:10:23 +05:30
PhaneeshB
c482ab78da fix second vic clearing for low mem device 2023-07-19 23:10:23 +05:30
Vivek Khandelwal
4be80f7158 Add support for the Llama-2 model 2023-07-19 20:57:08 +05:30
AyaanShah2204
536aba1424 unpinned torch_mlir (#1668)
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
20230719.828
2023-07-19 06:28:00 -07:00
Ean Garvey
dd738a0e02 small changes to opt_perf_comparison.py (#1670)
* Use longer prompts for OPT comparison script

* small tweaks
2023-07-19 06:26:50 -07:00
Daniel Garvey
8927cb0a2c set optional vmfb download (#1667) 20230718.827 2023-07-18 10:57:28 -07:00
Daniel Garvey
8c317e4809 fix cli for vicuna (#1666) 2023-07-18 10:03:40 -07:00
Vivek Khandelwal
b0136593df Add support for different compilation paths for DocuChat (#1665) 2023-07-18 09:49:44 -07:00
Vivek Khandelwal
11f62d7fac Minor fixes for MiniLM Training 2023-07-18 17:16:44 +05:30
powderluv
14559dd620 Update DocuChat as experimental (#1660) 2023-07-17 22:12:05 -07:00
AyaanShah2204
e503a3e8d6 fixed joblib import error (#1659) 20230717.825 2023-07-17 12:56:10 -07:00
AyaanShah2204
22a4254adf fixed pyinstaller path for langchain imports (#1658) 2023-07-17 12:19:21 -07:00
Vivek Khandelwal
ab01f0f048 Add Langchain model in SHARK (#1657)
* Add H2OGPT

* Add UI tab for h2ogpt

* Add source files from h2ogpt

* Add the rest of the files

* Add h2ogpt support

* Add SHARK Compilation support for langchain model for cli mode

---------

Co-authored-by: George Petterson <gpetters@protonmail.com>
2023-07-17 09:58:15 -07:00
Phaneesh Barwaria
c471d17cca codegen API (#1655) 20230716.824 2023-07-16 20:00:39 -07:00
Stefan Kapusniak
a2a436eb0c SD - Add repeatable (batch) seeds option (#1654)
* Generates the seeds for all batch_count batches being run up front
rather than generating the seed for a batch just before it is run.
* Adds a --repeatable_seeds argument defaulting to False
* When repeatable_seeds=True, the first seed for a set of batches will
also be used as the rng seed for the subsequent batch seeds in the run.
The rng seed is then reset.
* When repeatable_seeds=False, batch seeding works as currently.
* Update scripts under apps/scripts that support the batch_count
argument to also support the repeatable_seeds argument.
* UI/Web: Adds a checkbox element on each SD tab after batch count/size
for toggling repeatable seeds, and update _inf functions to take
this into account.
* UI/Web: Moves the Stop buttons out of the Advanced sections and next
to Generate to make things not fit quite so badly with the extra UI
elements.
* UI/Web: Fixes logging to the upscaler output text box not working
correctly when running multiple batches.
20230715.823
2023-07-15 16:22:41 -07:00
powderluv
1adb51b29d Update docker README.md 2023-07-15 14:31:56 -07:00
anush elangovan
aab2233e25 Add a dev Ubuntu 22.04 docker image 2023-07-15 16:25:37 +00:00
jinchen62
e20cd71314 Change to a separate pass to unpack quantized weights (#1652) 2023-07-15 04:54:53 -07:00
powderluv
5ec91143f5 add a HF accelerate requirement (#1651) 20230714.822 20230714.821 2023-07-14 05:56:12 -07:00
Ean Garvey
7cf19230e2 add perf comparison script for opt. (#1650) 20230713.820 2023-07-13 13:29:48 -05:00
powderluv
1bcf6b2c5b pin diffusers to 0.18.1 (#1648) 20230713.819 2023-07-13 01:02:24 -07:00
jinchen62
91027f8719 Remove done TODOs, a sup PR for #1644 (#1647) 2023-07-12 23:30:45 -07:00