microsoft/Olive

Issues

• Unable to export a quantized Phi-3.5-mini-instruct model

  #1527 opened 5 days ago by adamdougal
  0

• ORTModelUnet config file not found after initial run

  #1526 opened 5 days ago by willkara
  0

• BERT has not final model

  #1439 opened 11 days ago by dangokuson
  4

• onnx GPU optimization

  #1514 opened 16 days ago by heman-CL
  2

• [FR]: Shared cache when running on Azure Machine Learning compute

  #1508 opened 18 days ago by cecheta
  2

• `olive shared-cache` throws exception

  #1509 opened 18 days ago by cecheta
  2

• Using a local model in input_model causes SameFileError in MergeAdapters Pass

  #1442 opened a month ago by samuel100
  0

• [FR]: Supply dynamic_shapes in ONNX export when `dynamo=True`

  #1478 opened a month ago by justinchuby
  0

• olive auto-opt does not generate genai_config.json when --provider option is given

  #1471 opened a month ago by natke
  1

• Stable Diffiusion example does not exist at all

  #1475 opened a month ago by BrickDesignerNL
  1

• ORTStableDiffusionXLPipeline received config, but do not accept those arguments.

  #1470 opened a month ago by jesenzhang
  0

• olive auto-opt with --model_builder --provider DmlExecutionProvider and --adapter errors out

  #1464 opened a month ago by natke
  0

• Convert-adapters method output file name error when given name has dot inside

  #1459 opened a month ago by liuyunms
  1

• `SharedCache.update_model_config` uses undefined attributes and functions

  #1463 opened a month ago by jambayk
  0

• olive auto-opt with --model_builder seems to run the onnxruntime optimizer then crashes

  #1460 opened a month ago by natke
  0

• --use_model_builder does not work with olive auto-opt

  #1454 opened a month ago by natke
  3

• --provider does not work with olive auto-opt

  #1449 opened a month ago by natke
  3

• Shape error with .onnx_adapter after convert-adapter

  #1451 opened 2 months ago by natke
  4

• Phi3 example error evaluators -> common_evaluator gqa_transformer_prompt_dummy_data not found in {} (type=value_error)

  #1447 opened 2 months ago by MikeYeager
  1

• ONNX Runtime AudioDecoder Error on Olive with Whisper Model

  #1362 opened 3 months ago by mridulrao
  4

• Use model builder does not work with capture-onnx-graph

  #1450 opened 2 months ago by natke
  0

• Unable to get dummy inputs for the model

  #1397 opened 2 months ago by dangokuson
  0

• TypeError: expected str, bytes or os.PathLike object, not NoneType

  #1377 opened 2 months ago by dangokuson
  0

• [Bug]: ImportError: cannot import name 'load_model'

  #1406 opened 3 months ago by Pilaf4567
  1

• [Flux1] - Type parameter (T) of Optype (Einsum) bound to different types

  #1287 opened 4 months ago by saddam213
  6

• ONNX quantization MatMul4BitsQuantizer model failed

  #1411 opened 2 months ago by DimQ1
  1

• ValidationError: A lot of validation errors for RunConfig

  #1365 opened 2 months ago by dangokuson
  1

• ONNX model optimization failed.

  #1405 opened 3 months ago by prashant-saxena
  0

• phi3 inference RuntimeError

  #1391 opened 3 months ago by khmyznikov
  2

• getting error while running llama2/bert on GPU

  #1279 opened 5 months ago by himanshushukla12
  6

• Whisper olive setup error

  #1312 opened 4 months ago by liuyulvv
  1

• getting error while finetuning llama2 using qlora

  #1315 opened 4 months ago by himanshushukla12
  4

• capture-onnx-graph CLI Bug: list append()

  #1348 opened 3 months ago by samuel100
  0

• Mistral int4 error

  #1330 opened 4 months ago by eddan168
  1

• Unable to use batch prediction with generated Whisper model using Olive

  #1288 opened 3 months ago by david-sitsky
  7

• Mistral optimization(GPU) for a locally saved model, Failed to run Olive on gpu-cuda.

  #1341 opened 4 months ago by tjinjin95
  1

• Mistral Run Optimization(GPU) program end without generate model

  #1340 opened 4 months ago by tjinjin95
  0

• Error when attempting to optimize stable-diffusion with directML

  #1267 opened 5 months ago by fragfeaster777
  6

• KeyError: 'unet_dataloader' occurs when optimizing unet in stable_diffusion_xl.py

  #1327 opened 4 months ago by giocafe
  1

• error while inferencing the mistral LLM

  #1309 opened 4 months ago by himanshushukla12
  0

• [FR]: Could not find a version that satisfies the requirement ort-nightly-directml==1.18.0 (from version: none)

  #1280 opened 5 months ago by purejomo
  3

• Missing implementation error for CoreML

  #1299 opened 4 months ago by thewh1teagle
  1

• whisper transcriptions is empty

  #1291 opened 4 months ago by thewh1teagle
  2

• Very slow inference of optimized whisper gpu

  #1300 opened 4 months ago by thewh1teagle
  0

• Optimize whisper medium gpu failed

  #1298 opened 4 months ago by thewh1teagle
  0

• LLM Optimization with DirectML reply only displays "O"s

  #1282 opened 5 months ago by yichunx1
  3

• Getting KeyError: 'input_model' when trying to optimize whisper-tiny.en model

  #1283 opened 5 months ago by mram0509
  1

• Whisper optimization using ORT toolchain

  #1264 opened 5 months ago by reeselevine
  2

• [FR]: Gather per-pass output logs

  #1269 opened 5 months ago by skywall
  2

• Whisper tool_command_args "skip_special_tokens": false config ignored

  #1274 opened 5 months ago by david-sitsky
  1