Skip to content

Issues: nod-ai/SHARK-ModelDev

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

213 Open 421 Closed
213 Open 421 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

Coordinate with IREE stable release process and implement any missing process/automation
#281 opened Dec 19, 2023 by stellaraccident
llama_test.py fail when bumping iree to 20231130.724 enhancement New feature or request
#221 opened Dec 5, 2023 by AmosLewis
5 tasks
[tracking] ONNX Op Support tracking-issue Tracking Issue
#215 opened Dec 1, 2023 by saienduri 100+
@rsuderman @renxida
@PhaneeshB @AmosLewis @Shukla-Gaurav @aldesilv @daveliddell @vivekkhandelwal1 @kumardeepakamd
36
how to convert any LLama model to MLIR format?
#214 opened Dec 1, 2023 by louwangzhiyuY
6
AttributeError: 'NoneType' object has no attribute 'shape' when trying to torch.compile nanoGPT model
#206 opened Nov 24, 2023 by yuanfz98
1
When is the best time to support cuda device in SHARK-Turbine?
#205 opened Nov 23, 2023 by tianxiangsong
3
Integrate quantization pass with CompiledModule
#183 opened Nov 17, 2023 by IanNod
1
2
Cleanly map new external parameters created in MMGroupQuantRewriterPass
#181 opened Nov 17, 2023 by IanNod
1
Support creating uninitialized globals for dynamic shaped tensors
#171 opened Nov 10, 2023 by stellaraccident
Expose FloatType to Python (vs just individual F32Type, F64Type, etc)
#170 opened Nov 10, 2023 by stellaraccident
Expose function to get default value for type to Python
#169 opened Nov 10, 2023 by stellaraccident
Problem about torch output tensor is alias of input tensor
#167 opened Nov 10, 2023 by SuperCarrot2012
"pip install -e ." does not correctly look in pip release links
#164 opened Nov 10, 2023 by dan-garvey
5
torch.aten.adaptive_max_pool3d
#160 opened Nov 5, 2023 by dan-garvey
@zjgarvey
StableDiffusion
#152 opened Nov 3, 2023 by stellaraccident
@aviator19941
9
Remove RankedTensorType dependence on a context Location
#145 opened Oct 31, 2023 by stellaraccident Path to V1
FuncOp constructor requires a context-manager context and does not accept an explicit loc.
#138 opened Oct 31, 2023 by stellaraccident Path to V1
Dump artifacts to a directory and log command lines for CL tool use
#136 opened Oct 31, 2023 by stellaraccident
Create IR proxies for procedural non-tensor types
#135 opened Oct 31, 2023 by stellaraccident Path to V1
Add MLIR API support for creating an insertion point after an operation
#133 opened Oct 31, 2023 by stellaraccident Path to V1
Add more comprehensive type promotion hierarchy to procedural binary operators
#132 opened Oct 31, 2023 by stellaraccident Path to V1
Infer tensor_splat dtype if missing
#131 opened Oct 31, 2023 by stellaraccident Path to V1
Support IREE raw element types in addition to torch dtypes
#130 opened Oct 31, 2023 by stellaraccident Path to V1
Two phase export supporting function call dependence
#129 opened Oct 31, 2023 by stellaraccident Path to V1
Consistent exception handling and user-accessible messaging
#127 opened Oct 31, 2023 by stellaraccident Path to V1
ProTip! What’s not been updated in a month: updated:<2025-02-01.