[go: nahoru, domu]
Skip to content

Pull requests: quic/aimet

New pull request New
Clear current search query, filters, and sorts
15 Open 1,801 Closed
15 Open 1,801 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

Modify quantizer type based on encoding provided when strict=False
#3141 by quic-gsaichai was merged Jul 3, 2024 Loading…
1
@quic-gsaichai
Remove manual CMake build from Dockerfiles.
#3137 by quic-michof was merged Jul 3, 2024 Loading…
Issue add exceptions for loading lora weights
#3136 by quic-klhsieh was merged Jul 2, 2024 Loading…
1
@quic-mangal @quic-klhsieh
Replace multiply operator with elementwise_ops.Multiply
#3134 by quic-geunlee was merged Jul 2, 2024 Loading…
@quic-geunlee
Add QuantizationMixin API documentation
#3133 by quic-mtuttle was merged Jul 2, 2024 Loading…
@quic-mtuttle
Add blockwise quantization docs
#3132 by quic-klhsieh was merged Jul 2, 2024 Loading…
1
@quic-klhsieh
Adding migration guide for Quantsim 1.0 to Quantsim 2.0
#3129 by quic-pdangi was merged Jul 2, 2024 Loading…
1
@quic-pdangi
Adding overview page
#3127 by quic-pdangi was merged Jul 2, 2024 Loading…
1
@quic-pdangi
Remove duplicate quantization of some quantized nn modules
#3126 by quic-kyunggeu was merged Jul 1, 2024 Loading…
@quic-kyunggeu
Use plain torch tensor internally
#3125 by quic-kyunggeu was merged Jul 1, 2024 Loading…
@quic-kyunggeu
Correctly capture activations to be quantized
#3124 by quic-rgite was merged Jul 1, 2024 Loading…
1
@quic-rgite
Add support for op parameters derived from constant op
#3122 by quic-rgite was merged Jul 1, 2024 Loading…
1
@quic-rgite
Add feature to make ONNX node output name unique
#3120 by quic-geunlee was merged Jul 1, 2024 Loading…
@quic-geunlee
Remove RESTORE_ONNX_MODEL_INITIALIZERS and make it run default
#3119 by quic-geunlee was merged Jun 29, 2024 Loading…
@quic-geunlee
Replace temp directory using tempfile module
#3118 by quic-hitameht was merged Jun 28, 2024 Loading…
@quic-hitameht
Fix unit tests failing with torch 1.13
#3117 by quic-mtuttle was merged Jul 2, 2024 Loading…
@quic-mtuttle
torch 2.2.2 updates for python 3.10 and python 3.8 aimet-torch
#3115 by quic-jpolizzi was merged Jul 1, 2024 Loading…
Add PEFT Conv2d lora layer
#3114 by quic-mangal was merged Jun 28, 2024 Loading…
Optimize torch tests
#3112 by quic-mtuttle was merged Jun 28, 2024 Loading…
@quic-mtuttle
Autoquant flow updation
#3111 by quic-saksrai was merged Jul 1, 2024 Loading…
1
@quic-saksrai
Fix load_encodings_to_sim for float encoding overrides
#3109 by quic-gsaichai was merged Jun 27, 2024 Loading…
1
@quic-gsaichai
Infer quantizer signedness when importing encodings
#3107 by quic-mtuttle was merged Jun 27, 2024 Loading…
@quic-mtuttle
QAT knowledge distillation code example for LLMs
#3106 by quic-kyunggeu was merged Jul 2, 2024 Loading…
@quic-kyunggeu
Make quantized tensors deep-copyable
#3105 by quic-kyunggeu was merged Jun 26, 2024 Loading…
@quic-kyunggeu
Fix typo in elementwise RSqrt
#3104 by quic-mtuttle was merged Jun 26, 2024 Loading…
@quic-mtuttle
ProTip! Type g i on any issue or pull request to go back to the issue listing page.