-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Issues: intel-analytics/ipex-llm
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
packaging.version.InvalidVersion: Invalid version: '2023.2.0-13089-cfd42bd2cb0-HEAD'
Nano
user issue
#9540
opened Nov 27, 2023 by
Lucas-Wye
[Nano] Support non-tensor input to export to onnx/openvino for tracing
Nano
#8060
opened Apr 17, 2023 by
HensonMa
Loading…
11 tasks done
Nano: add sample_size limit to quantize of ipex and jit_int8
Nano
#7804
opened Mar 8, 2023 by
ACupofAir
Loading…
Nano: Fix issue for bigdl-nano-init --perf
Nano
#7312
opened Jan 18, 2023 by
TheaperDeng
Loading…
1 task
Too long warm-up time for
TorchScript
models
Chronos
Nano
user issue
#7062
opened Dec 21, 2022 by
liangs6212
Nano: add how to guide for inference in bf16 precision
document
Nano
#7042
opened Dec 20, 2022 by
ACupofAir
Loading…
Nano - Inference optimizer: channel last support for 3D inputs
Nano
#6810
opened Nov 30, 2022 by
Siritao
pytorch_ipex (inc 1.13.1) will fail on hardware with BF16 instruction set
Chronos
Nano
#6694
opened Nov 21, 2022 by
rnwang04
1 of 2 tasks
[API Doc] Syntax-related issues and other possible problems in Nano API doc
API
document
Nano
#6590
opened Nov 14, 2022 by
AndyLuo1029
30 tasks
Nano: we need to force fp32/bf16/int8 precision usage and expose property setting for openvino
Nano
#6473
opened Nov 7, 2022 by
TheaperDeng
Nano: we should support a flag that indicates the model does not have batchsize dim
Nano
#6391
opened Nov 1, 2022 by
TheaperDeng
Nano: multiple-instance training alignment with single-instance training
Nano
#6295
opened Oct 26, 2022 by
TheaperDeng
3 tasks
Previous Next
ProTip!
no:milestone will show everything without a milestone.