Skip to content

Pull requests: nod-ai/shark-ai

New pull request New
39 Open 433 Closed
39 Open 433 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

(shortfin-sd) Validate size of downloaded artifacts.
#560 opened Nov 18, 2024 by monorimet Loading…
(shortfin-sd) Cleanup fiber distribution, logging, error handling.
#555 opened Nov 17, 2024 by monorimet Loading…
Update version back to 3.0.0 for stable release.
#553 opened Nov 15, 2024 by ScottTodd Loading…
Recommend installing torch cpu ahead of shark-ai.
#552 opened Nov 15, 2024 by ScottTodd Loading…
Add T5 LM v1.1 encoder
#550 opened Nov 15, 2024 by sogartar Loading…
14
(shark-ai CI) Split out install shortfin ci step, which takes a long time.
#549 opened Nov 15, 2024 by renxida • Draft
Group llm integration test output using github ::group::
#546 opened Nov 15, 2024 by renxida Loading…
2
Build nightly shark-ai -package
#535 opened Nov 15, 2024 by marbre Loading…
10
[shortfin] Merge Windows and Linux workflows
#510 opened Nov 14, 2024 by marbre • Draft
[shortfin] Implement async alloc/dealloc of buffers.
#507 opened Nov 14, 2024 by stellaraccident Loading…
Use IREE versions pinned in requirements file
#503 opened Nov 13, 2024 by marbre Loading…
[shortfin] Read IREE version from text file
#502 opened Nov 13, 2024 by marbre Loading…
3
[shortfin] Add port specifier to send_request.py
#500 opened Nov 13, 2024 by AWoloszyn Loading…
Sglang User Doc documentation Improvements or additions to documentation
#498 opened Nov 13, 2024 by stbaione Loading…
@stbaione
5
Make config.json consistent between shortfin and sharktank
#487 opened Nov 12, 2024 by renxida • Draft
2
Add workflow to test packages
#473 opened Nov 11, 2024 by marbre Loading…
7
[sharktank] Add perplexity CI to sharktank dashboard
#466 opened Nov 9, 2024 by archana-ramalingam Loading…
9
Add prefill 8B f16 torch sdpa test, update tests with compile flags and tp flags, with nightly iree
#456 opened Nov 8, 2024 by aviator19941 Loading…
6
[sharktank] Split Perplexity CI
#452 opened Nov 8, 2024 by archana-ramalingam Loading…
7
Delete sharktank/serving_poc code that is replaced with shortfin.
#429 opened Nov 5, 2024 by ScottTodd Loading…
1
Add trace_tensors op
#425 opened Nov 5, 2024 by sogartar Loading…
Fix cache config inconsistency between shortfin and sharktank
#406 opened Nov 1, 2024 by renxida • Draft
1
4
Add IREE numerics test for Llama 3.1 8B FP16 TP8
#394 opened Oct 31, 2024 by sogartar Loading…
1
Add class that implements BaseCausalLMModel but is backed by an IREE module
#393 opened Oct 31, 2024 by sogartar Loading…
3
Add block seq len and attention/activation dtype args to LLM export script
#391 opened Oct 31, 2024 by sogartar Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.