Skip to content

Issues: nod-ai/shark-ai

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

68 Open 28 Closed
68 Open 28 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Enable building shortfin's Rust dependencies on Windows infra General category for infrastructure-related requests for common triaging and prioritization
#620 opened Nov 27, 2024 by marbre
Manage page allocations through a PageAllocation object, rather than straight in InferenceExecRequest
#607 opened Nov 25, 2024 by renxida
1
3
(shortfin) Parameterized pytest fixtures for testing over cpu and gpu
#599 opened Nov 23, 2024 by renxida
[tracking] Minimal prefix-sharing kv cache
#593 opened Nov 22, 2024 by renxida
8 of 20 tasks
Rework GitHub Actions workflows to build packages --> test packages
#584 opened Nov 21, 2024 by ScottTodd
@ScottTodd @marbre @renxida
4
Auto-add copyright / license header during precommit
#572 opened Nov 19, 2024 by renxida
1
Fix broken punet after fp8 changes
#571 opened Nov 19, 2024 by dan-garvey
@dan-garvey
(shortfin-sd) Upstream iree.build pieces where applicable.
#563 opened Nov 18, 2024 by monorimet
@monorimet
(shortfin.array) What if we had a context manager for briefly getting a host copy of a device array?
#556 opened Nov 17, 2024 by renxida
1
[shortfin] Windows builds failing when compiling compound literals bug Something isn't working
#534 opened Nov 15, 2024 by ScottTodd
2
(shortfin-sd) Model artifact building/fetching improvements.
#525 opened Nov 14, 2024 by monorimet
4 tasks
(shortfin-sd) Add/verify gfx90a support.
#518 opened Nov 14, 2024 by monorimet
@vinayakdsci
(shortfin-sd) Server segfaults at startup on python3.13 free-threaded
#516 opened Nov 14, 2024 by monorimet
1
gfx1100 is missing a flagsfile.
#515 opened Nov 14, 2024 by AWoloszyn
@monorimet
1
Shark V1 Nov 2024 Release Testing Bash
#512 opened Nov 14, 2024 by pdhirajkumarprasad
6
(shortfin) Cannot build with clang 19.1.3
#497 opened Nov 13, 2024 by AWoloszyn
[sharktank] Test failures with torch>=2.4.0
#495 opened Nov 13, 2024 by marbre
1
Improve Method for Shutting Down Shortfin LLM Server
#490 opened Nov 12, 2024 by stbaione
(shortfin) Fix CPX device visibility specification.
#486 opened Nov 12, 2024 by monorimet
(shortfin-sd) Verify download results.
#485 opened Nov 12, 2024 by monorimet
[llama decomposed]: Parameter files missing for different decomposed models
#472 opened Nov 11, 2024 by pdhirajkumarprasad
@dan-garvey
4
Improve App Integration Test Ergonomics
#464 opened Nov 9, 2024 by stbaione
[amdgpu] If exceeding ulimit file handle limit while constructing HIP devices, memory corruption and process crash.
#463 opened Nov 9, 2024 by stellaraccident
@AWoloszyn
(shortfin-sd) Report max latency.
#460 opened Nov 8, 2024 by monorimet
@monorimet
Overly strict sharktank version dependencies
#459 opened Nov 8, 2024 by saienduri
1
ProTip! What’s not been updated in a month: updated:<2024-10-30.