microsoft/Olive

Issues

• [FR]: Add support for Stable Diffusion 3 on DirectML

  #1251 opened 5 months ago
  3

• nice pcode

  #1248 opened 5 months ago
  0

• Exporting to ONNX with kv_cache

  #1240 opened a month ago
  8

• optimizing whisper without audio_decoder

  #1236 opened 5 months ago
  3

• [bug] Failed to perform inference on the optimized distil-large-v3 using the test_transcription.py

  #1231 opened 5 months ago
  6

• The float16 unet model of stable-diffusion-2-1 outputs NAN results

  #1223 opened 5 months ago
  3

• Whisper with DirectML: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running WhisperBeamSearch node

  #1221 opened 6 months ago
  0

• Whisper with DirectML EP not working: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for DecoderMaskedMultiHeadAttention(1) node with name 'Attention_0'

  #1213 opened 6 months ago
  14

• [Whisper] convert with FP32 running failed

  #1207 opened 5 months ago
  4

• vae_encoder_gpu-dml_footprints.json file not found when converting stable diffusion xl base model

  #1202 opened 6 months ago
  6

• Using Whisper for Chinese ASR in iOS may occasionally output illegal UTF-8 strings.

  #1197 opened 6 months ago
  2

• Failed to optimize Whisper tiny by gpu (CUDA)

  #1196 opened 6 months ago
  0

• Failed on optimization step of Unet - Intel Meteor Lake Processor

  #1194 opened 6 months ago
  0

• data_config: data_name is not None but olive always said it is None

  #1193 opened 6 months ago
  3

• [Question]: How do you use a finetuned model for mobile

  #1186 opened 7 months ago
  1

• [FR]: Finetuning QLoRA adapters and swapping

  #1182 opened 7 months ago
  1

• [Bug]: Optimization of Unet fails - AMD RDNA3.5 Strix Point Processor

  #1170 opened 7 months ago
  2

• Get Error while optimizing SDXL of DirectML example

  #1165 opened 7 months ago
  1

• "num_images" doesn't work for the example of directml stable_diffusion_xl.

  #1164 opened 7 months ago
  1

• huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.'

  #1158 opened 7 months ago
  0

• onnx

  #1156 opened 7 months ago
  0

• safetensor model

  #1153 opened 7 months ago
  0

• Llava-7b model Conversion to ONNX and Latency Optimization - OOM error (even after setting paging file size)

  #1144 opened 7 months ago
  2

• Enabling openai/whisper-large-v3 using olive-ai-0.6.0 [onnxruntime-gpu: 1.17.1] on Intel CPU/GPU is not supporting

  #1134 opened 8 months ago
  2

• Vitis quantization is broken with ORT 1.18

  #1125 opened 8 months ago
  2

• status.IsOK() was false. Tensor shape cannot contain any negative value

  #1108 opened 8 months ago
  1

• Error on the Generate an ONNX model and optimize step

  #1105 opened 8 months ago
  5

• Failed to run symbolic shape inference when doing LLM Optimization with DirectML

  #1093 opened 8 months ago
  11

• Exception while running SD XL: Not enough memory resources are available to complete this operation

  #1079 opened 8 months ago
  1

• Olive workflow for mistral model optimization does not work

  #1075 opened 8 months ago
  17

• pydantic.error_wrappers.ValidationError: 7 validation errors for RunConfig

  #1074 opened 8 months ago
  1

• [FR]: FlashAttention support for Whisper

  #1065 opened 7 months ago
  1

• Missing dependency: psutil

  #1043 opened 9 months ago
  2

• GenAIModelExporter Component - parameter mismatch

  #1042 opened 8 months ago
  3

• whisper pipeline corrupting the model, unable to run on DML EP

  #1031 opened 8 months ago
  1

• Whisper model does not work If you add a flag --enable_timestamps

  #1026 opened 9 months ago
  7

• Whisper-medium conversion failed

  #1023 opened 8 months ago
  8

• Whisper model converted via onnxruntime 1.17.1 won't work

  #1014 opened 9 months ago
  5

• models_rank.json issue

  #1007 opened 9 months ago
  4

• Any workarounds to convert phi-2 model on Windows

  #966 opened 10 months ago
  3

• Conversion of some models are buggy

  #939 opened 10 months ago
  0

• This is an invalid model

  #935 opened 10 months ago
  4

• SDXL crashing when trying to run

  #930 opened 10 months ago
  3

• [Bug] Optimization step for unet fails after 'Protobuf parsing failed'

  #926 opened 8 months ago
  10

• I don't have models/optimized/llama_v2 folder after I've run python llama_v2.py --optimize

  #905 opened a year ago
  8

• NOT_IMPLEMENTED : Could not find an implementation for BeamSearch(1) node with name 'BeamSearch_node'

  #900 opened 10 months ago
  6

• Error with search strategic.py 'Conversion Merged" has no output models for Llama2 optimization

  #897 opened a year ago
  2

• UnboundLocalError: local variable 'output_model_json' referenced before assignment

  #871 opened a year ago
  9

• Unable to perform Whisper GPU Int8 conversion

  #869 opened a year ago
  11

• Missing file https://github.com/microsoft/Olive/blob/main/docs/source/overview/configuring_pass

  #866 opened a year ago
  2