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.

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

remove pre/post callbacks #92

Merged
merged 43 commits into from
Apr 12, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
43 commits
Select commit Hold shift + click to select a range
cb95bf8
removing pre/post - WIP
mmoskal Mar 27, 2024
ae92ea2
Merge branch 'main' into pre_post
mmoskal Mar 27, 2024
c6dc3fb
pre/post code complete
mmoskal Mar 27, 2024
239d1d9
error fixes
mmoskal Mar 27, 2024
4740c6e
fix warnings
mmoskal Mar 28, 2024
0f651a9
working on pyctrl
mmoskal Mar 28, 2024
d8b70f6
bring prompt APIs back in {js,py}ctrl
mmoskal Mar 28, 2024
67ad78f
re-work to only use mid
mmoskal Mar 28, 2024
6a7f8cb
add tokens_repr(); bugfix
mmoskal Mar 29, 2024
874f6b2
add post_process back
mmoskal Mar 29, 2024
8754af3
re-gen files
mmoskal Mar 29, 2024
7af1d6f
add limited forking
mmoskal Mar 29, 2024
abf446a
fork fixes
mmoskal Mar 29, 2024
74de675
don't do the EOS->space auto-replacement
mmoskal Mar 29, 2024
b6c443a
make jsctrl work with only mid callback
mmoskal Apr 3, 2024
ef7c9dd
install guidance (for deps) in docker
mmoskal Apr 3, 2024
c3ab1c1
Add wasm timer resolution option to server.sh script
mmoskal Apr 3, 2024
dfe5755
make the gctrl work again
mmoskal Apr 3, 2024
ebf3dab
add aici_native crate
mmoskal Apr 5, 2024
75313a0
remove unused deps
mmoskal Apr 5, 2024
3f01040
fix build
mmoskal Apr 5, 2024
f764fc8
move core parser to library
mmoskal Apr 5, 2024
53a4658
cleanup
mmoskal Apr 5, 2024
a436181
add TokenizerEnv
mmoskal Apr 5, 2024
75829d1
minor
mmoskal Apr 6, 2024
a724889
Update TokenParser struct to make token_env field public
mmoskal Apr 6, 2024
b1b9b4d
improvements to byte forcing
mmoskal Apr 8, 2024
213b7b3
fix comment
mmoskal Apr 8, 2024
c02454a
implement max_tokens
mmoskal Apr 10, 2024
9f27a0e
updating python code to deal with no pre/post
mmoskal Apr 11, 2024
c299820
token splicing in vllm
mmoskal Apr 12, 2024
df5a541
update vllm
mmoskal Apr 12, 2024
7ec0488
add --skip and --only to test driver
mmoskal Apr 12, 2024
6a48502
start declctrl port to pre/post removal branch
mmoskal Apr 12, 2024
c6a51e6
add get_config() host API (fork support detection so far)
mmoskal Apr 12, 2024
a885ba4
add "inference_caps" LLM->aicirt
mmoskal Apr 12, 2024
4c079a2
add fork_supported() function; fix tests
mmoskal Apr 12, 2024
9479488
test noops
mmoskal Apr 12, 2024
7b8aa6d
Merge branch 'pre_post' into declctrl_pre_post
mmoskal Apr 12, 2024
08f21d1
add aicirt --cap-fork; drop inference_cap req
mmoskal Apr 12, 2024
2d58639
fix typo
mmoskal Apr 12, 2024
7804d11
fix declctrl
mmoskal Apr 12, 2024
2f655cd
enable submodules in actions
mmoskal Apr 12, 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
3 changes: 3 additions & 0 deletions .devcontainer/Dockerfile-cuda
Original file line number Diff line number Diff line change
Expand Up @@ -14,3 +14,6 @@ RUN ln -s /usr/local/lib/python3.10/dist-packages/nvidia/cuda_runtime/lib/libcud
RUN apt-get install -y linux-tools-`uname -r`

RUN source /usr/local/nvm/nvm.sh && npm install -g yarn

# we mostly need guidance deps
RUN pip install guidance
1 change: 1 addition & 0 deletions .devcontainer/vllm/devcontainer.json
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
"extensions": [
"ms-python.python",
"ms-python.black-formatter",
"eeyore.yapf",
"1YiB.rust-bundle",
"dtsvet.vscode-wasm",
"ms-vscode.cpptools",
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/aicirt-release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@ jobs:

steps:
- uses: actions/checkout@v3
with:
submodules: true
- run: rustup target add wasm32-wasi
- uses: Swatinem/rust-cache@v2
with:
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/aicirt.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ jobs:

steps:
- uses: actions/checkout@v3
with:
submodules: true
- run: rustup target add wasm32-wasi
- uses: Swatinem/rust-cache@v2
with:
Expand Down
Loading
Loading