Skip to content

Pull requests: Xilinx/brevitas

New pull request New
23 Open 498 Closed
23 Open 498 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

Fix (ptq/bias_correction): remove unnecessary forward pass
#980 opened Jul 3, 2024 by Giuseppe5 Loading…
Feat (tests): extended minifloat unit tests
#979 opened Jul 2, 2024 by alexredd99 Loading…
Various SDXL quantization fixes
#977 opened Jun 25, 2024 by nickfraser Loading…
5 of 6 tasks
Feat: Support for Groupwise (MX) quantization
#971 opened Jun 17, 2024 by Giuseppe5 Loading…
Fix (graph/bias_correction): Fix when layer parameters are offloaded to accelerate
#962 opened May 29, 2024 by nickfraser Loading…
Feat (examples/llm): Convert BertAttention to a quantizable version
#961 opened May 27, 2024 by nickfraser Loading…
[DO NOT MERGE] Feat (tests/actions): Updated tests to use python=3.10 instead of python=3.8
#959 opened May 23, 2024 by nickfraser Loading…
@nickfraser
1
Feat (gpfq): separate float and quant forward pass for speedup
#955 opened May 16, 2024 by fabianandresgrob Loading…
Feat: Extend ptq_evaluate to allow switching between torchvision and timm datsets
#946 opened Apr 30, 2024 by costigt-dev • Draft
1 of 14 tasks
1
Dev quant squeeze
#941 opened Apr 21, 2024 by ScXfjiang Loading…
2 tasks done
6
HQO for scale/zero point
#937 opened Apr 17, 2024 by Giuseppe5 Loading…
2
Added some preliminary unit tests to the CNNs 'quantize_model'
#927 opened Mar 30, 2024 by OscarSavolainenDR Loading…
22
Feat (gpxq): exposing A2GPxQ implementation to gpxq_mode
#925 opened Mar 27, 2024 by i-colbert • Draft
Feat: Added ONNX export to BNN-PYNQ example
#916 opened Mar 21, 2024 by nickfraser Loading…
1 of 3 tasks
@nickfraser
Feat (equalize): Adding l1-norm equalization criteria
#914 opened Mar 20, 2024 by i-colbert • Draft
Feat (quant-channel-splitting): support channel splitting after quantization
#912 opened Mar 19, 2024 by fabianandresgrob Loading…
Improvement: Change review_requested trigger to issue_comment trigger for full test suite infrastructure Anything related to CI/CD
#895 opened Mar 6, 2024 by costigt-dev Loading…
6 of 14 tasks
1
@costigt-dev
7
fix: add runtime_shape argument in batchnorm-related classes to match…
#804 opened Jan 23, 2024 by euphoria0-0 Loading…
1
Feat: improve Brevitas compatibility with torch.compile
#785 opened Dec 13, 2023 by nickfraser • Draft
@nickfraser
Fix (llm): add checks for group dimensions
#751 opened Nov 7, 2023 by Giuseppe5 Loading…
1
Feat (llm): export to MatMulNBits
#733 opened Oct 20, 2023 by Giuseppe5 Loading…
4
Fix UserWarning: Defining your __torch_function__ as a plain method is deprecated and will be an error in future, please define it as a classmethod.
#565 opened Mar 28, 2023 by V0XNIHILI Loading…
3
fixed wrong runtime shape inference for BatchNorm1dToQuantScaleBias
#465 opened Nov 28, 2022 by green-cabbage Loading…
5
ProTip! Filter pull requests by the default branch with base:master.