Skip to content

Pull requests: nod-ai/shark-ai

New pull request New
45 Open 591 Closed
45 Open 591 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Update nightly llama benchmarking tests
#754 opened Jan 4, 2025 by aviator19941 Loading…
[sharktank] Revert "[llama] Added the fused rotary embedding kernel (#719)"
#752 opened Jan 4, 2025 by archana-ramalingam Loading…
Flux vae
#750 opened Jan 3, 2025 by IanNod Loading…
Make path manipulation play nice with symlinks by deferring symlink resolution
#749 opened Jan 3, 2025 by sogartar Loading…
3
Bump IREE deps to 3.1.0rc20250103.
#747 opened Jan 3, 2025 by ScottTodd • Draft
4
Update more pins to IREE version 3.1.0rc20241220.
#746 opened Jan 3, 2025 by ScottTodd • Draft
3
[Tuner] Add support for TileAndFuse and multi-dim contractions
#745 opened Jan 3, 2025 by Max191 • Draft
increase app_tests/integration_tests/llm/utils.py server start timeout
#743 opened Jan 3, 2025 by renxida • Draft
1
Adds FLUX.1 service to shortfin apps.
#742 opened Jan 3, 2025 by monorimet Loading…
[shortfin] Zero out kv cache pages during allocation
#738 opened Jan 2, 2025 by rsuderman Loading…
1
Implement script to cleanup user-facing commands
#733 opened Jan 1, 2025 by vinayakdsci Loading…
46
make app_tests log subprocess stdout and stderr upon failure
#731 opened Dec 30, 2024 by renxida • Draft
pin iree compiler versions to temporarily mitigate #729 iree rc20241230 inconpatibility
#730 opened Dec 30, 2024 by renxida • Draft
1
Add meta llama 3 ci test using local irpa on CI machine
#728 opened Dec 26, 2024 by renxida • Draft
Bump IREE to latest commit on main.
#722 opened Dec 20, 2024 by ScottTodd • Draft
2
Fixed mixed precision contraction semantics for mmt_block_scaled_offset_q4_unsigned
#720 opened Dec 20, 2024 by Groverkss Loading…
Enable tokenizers in shortfin packages on Linux x86_64.
#688 opened Dec 12, 2024 by ScottTodd Loading…
1
3
Expanded sharded support for alternative sharding mechanisms
#680 opened Dec 12, 2024 by rsuderman Loading…
3
Fix iree_hal_buffer_subspan after change in iree.
#671 opened Dec 10, 2024 by AWoloszyn Loading…
Convert ci-shark-ai.yml to pkgci_shark_ai.yml.
#625 opened Nov 27, 2024 by ScottTodd • Draft
[sharktank] Update shark-ai CIs with latest install
#609 opened Nov 26, 2024 by archana-ramalingam Loading…
17
Create pkgci.yml and pkgci_build_packages.yml.
#589 opened Nov 22, 2024 by ScottTodd • Draft
8
(shortfin-sd) Interleave workers and their fibers by device.
#587 opened Nov 21, 2024 by monorimet Loading…
1
[tuner] Refactor tuner flow to use unified functions for models and dispatches
#577 opened Nov 20, 2024 by Max191 • Draft
10
[test] Change punet int8 model version
#569 opened Nov 19, 2024 by nithinsubbiah Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.