Skip to content

Pull requests: nod-ai/shark-ai

New pull request New
67 Open 794 Closed
67 Open 794 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

Install PyTorch for ROCM instead of CPU-only
#1032 opened Mar 4, 2025 by marbre Loading…
Reduce code duplication for ci-llama tests
#1031 opened Mar 4, 2025 by erman-gurses • Draft
Resolve CPU llm smoke / integration test hangs by temporarily removing 8-request testcases
#1028 opened Mar 4, 2025 by renxida • Draft
Make kv_cache read operation perform a single gather
#1027 opened Mar 4, 2025 by rsuderman Loading…
feature(shortfin_apps): move png construction to server side
#1025 opened Mar 3, 2025 by bjacobgordon Loading…
1
types(shortfin_apps): add missing annotations
#1024 opened Mar 3, 2025 by bjacobgordon Loading…
[temp pr] sharded llama ci with temporarily bumped iree
#1021 opened Mar 3, 2025 by renxida • Draft
Bump IREE requirement pins to 3.3.0rc20250303
#1020 opened Mar 3, 2025 by shark-pr-automator bot Loading…
@renxida
Add more logging to sharktank data tests infra General category for infrastructure-related requests for common triaging and prioritization
#1017 opened Mar 3, 2025 by erman-gurses • Draft
1
[tuner] add default attribute to tuning spec
#1016 opened Feb 28, 2025 by bangtianliu Loading…
1
[sharktank] Add common model config, export and compile
#1013 opened Feb 27, 2025 by sogartar Loading…
4
Refactor the SystemManager across shortfin apps
#1012 opened Feb 27, 2025 by KyleHerndon Loading…
Shortfin llm beam search
#1011 opened Feb 27, 2025 by stbaione • Draft
24
Refactoring more GenerateService functions across shortfin apps
#1010 opened Feb 27, 2025 by KyleHerndon Loading…
Initial pipeline parallelism support
#1008 opened Feb 25, 2025 by Alex-Vasile • Draft
3 of 6 tasks
52
Bump IREE requirement pins to 3.3.0rc20250227
#1003 opened Feb 25, 2025 by shark-pr-automator bot Loading…
@renxida
6
Fix llama fp8 benchmark test and remove decomposed benchmarking tests
#1000 opened Feb 25, 2025 by aviator19941 Loading…
1
Sharded integration tests
#995 opened Feb 24, 2025 by renxida • Draft
Cache shortfin llm integration test model artifacts in /shark-cache if it exists
#988 opened Feb 20, 2025 by renxida • Draft
Enable llama fp8 masked_flash_attention 8
#984 opened Feb 19, 2025 by AmosLewis • Draft
Test CI
#981 opened Feb 19, 2025 by stellaraccident • Draft
Speed-up all_gather by reducing buffer copies.
#979 opened Feb 18, 2025 by Alex-Vasile Loading…
Improve T5 encoder tests with more prompts and static context length
#976 opened Feb 17, 2025 by sogartar • Draft
1
[shortfin-sd] Add exports and support for scheduled unet, batch sizes.
#972 opened Feb 16, 2025 by monorimet Loading…
14
[sharktank][ci] Re-enable t5 data-dependent tests
#969 opened Feb 14, 2025 by renxida • Draft
@renxida
1
ProTip! Filter pull requests by the default branch with base:main.