Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Sync main and release branches #39

Merged
merged 42 commits into from
Jan 12, 2024
Merged

Sync main and release branches #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
42 commits
Select commit Hold shift + click to select a range
30c33bb
test: add test for the time limit stopping criteria
tjohnson31415 Oct 20, 2023
98584d3
Update to python 3.11 and flash-attention 2.3.2
njhill Oct 20, 2023
887a1cb
Update to latest miniconda / python 3.11.5
njhill Oct 20, 2023
1130840
Update poetry dependencies, in particular urllib 2.0.7
njhill Oct 21, 2023
3e34359
Add .model extension to default "extra" files downloaded with weights
njhill Oct 23, 2023
a39b8a8
feat: Basic script to test batching integrity of a deployed model
njhill Oct 24, 2023
536e6a0
Bump transformers minor version; fix TypicalLogitsWarper
njhill Oct 25, 2023
a8926f6
Revert TypicalLogitsWarper change for now
njhill Oct 26, 2023
1083fd0
Support for serving GPTQ quantized models
njhill Oct 26, 2023
ad33fc0
Update various rust and python dependencies
njhill Nov 1, 2023
188f39f
dep: update cryptography to address cve
anhuong Nov 2, 2023
27e0952
Update to protobuf 25.0 and onnxruntime 1.16.1
njhill Nov 2, 2023
6c670dd
Adding exllamav2 support for GPTQ models
cyang49 Nov 6, 2023
d31197b
Vectorized next token chooser for causal_lm
alex-jw-brooks Nov 7, 2023
7c48f48
Add prometheus metrics for tokenize API
njhill Nov 7, 2023
9e3fb05
Update to transformers 4.35 and update some rust TLS dependencies
njhill Nov 7, 2023
63142fc
fix: Always print CUDA memory summary
njhill Nov 8, 2023
f4060c0
fix: use torch instead of numpy to resolve device mismatch bug
tjohnson31415 Nov 8, 2023
7ad221f
feat: use HeterogeneousNextTokenChooser in seq2seq_lm
tjohnson31415 Nov 8, 2023
45842ad
refactor: increase scope of try block
tjohnson31415 Nov 8, 2023
2756820
Fix flash impl for "old" Falcon arch models (incl. falcon-7b)
njhill Nov 8, 2023
f3fc122
fix: fixes after testing causal_lm vectorization on GPU
tjohnson31415 Nov 9, 2023
d723faa
deps: update base image
anhuong Nov 9, 2023
1feed99
fix: Handle no max_batch_weight case for exllamav2 GPTQ
njhill Nov 9, 2023
642041d
Some minor token processing logic cleanup
njhill Nov 9, 2023
2c6e567
Fix return_top_n negative infinity bug
njhill Nov 9, 2023
a2b1ad0
feat: use HeterogeneousNextTokenChooser in flash_causal_lm (#301)
tjohnson31415 Nov 9, 2023
7c4745e
Update poetry dependency versions and tokio
njhill Nov 11, 2023
d4041c5
Use shared thread pool for tokenization (#396)
njhill Nov 13, 2023
47e8ba7
Break dependency on older vulnerable version of spin crate
njhill Nov 13, 2023
167a154
Fix PT compile warmup
njhill Nov 13, 2023
6004ea3
Update onnx dependencies
declark1 Nov 15, 2023
0ebc567
Update UBI base image
njhill Nov 15, 2023
85918c5
Don't include extra left padding in all_input_ids_tensor
njhill Nov 16, 2023
2470e7d
fix: repetition penalty bug if EOS and PAD tokens have the same id
tjohnson31415 Nov 16, 2023
87b8834
Add OWNER file
vaibhavjainwiz Jul 5, 2023
52925a9
Add a checking logic to delete miniconda directory
Jooho Sep 1, 2023
a1c2a3b
Ensure conda is updated
Xaenalt Aug 15, 2023
2472975
auto add new issues to ODH projects
heyselbi Oct 4, 2023
a57bdf1
Ensure final dockerfile updates packages
Xaenalt Nov 20, 2023
e1c7e21
deps: bump optimum to 1.16.1
dtrifiro Jan 10, 2024
03e3a60
Merge pull request #40 from dtrifiro/fix-build
openshift-merge-bot[bot] Jan 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions .github/workflows/auto-add-issues-to-project.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
name: Auto Add Issues to Tracking boards
on:
issues:
types:
- opened
jobs:
add-to-project:
name: Add issue to projects
runs-on: ubuntu-latest
steps:
- name: Generate github-app token
id: app-token
uses: getsentry/action-github-app-token@v2
with:
app_id: ${{ secrets.DEVOPS_APP_ID }}
private_key: ${{ secrets.DEVOPS_APP_PRIVATE_KEY }}
- uses: actions/[email protected]
with:
project-url: https://github.com/orgs/opendatahub-io/projects/40
github-token: ${{ steps.app-token.outputs.token }}
- uses: actions/[email protected]
with:
project-url: https://github.com/orgs/opendatahub-io/projects/45
github-token: ${{ steps.app-token.outputs.token }}
- uses: actions/[email protected]
with:
project-url: https://github.com/orgs/opendatahub-io/projects/42
github-token: ${{ steps.app-token.outputs.token }}
Loading