microsoft/Olive

Issues

• ValidationError: A lot of validation errors for RunConfig

  #1365 opened 13 days ago by dangokuson
  0

• Whisper olive setup error

  #1312 opened 2 months ago by liuyulvv
  1

• ONNX Runtime AudioDecoder Error on Olive with Whisper Model

  #1362 opened 14 days ago by mridulrao
  0

• getting error while finetuning llama2 using qlora

  #1315 opened 2 months ago by himanshushukla12
  4

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

  #1348 opened 22 days ago by samuel100
  0

• Mistral int4 error

  #1330 opened a month ago by eddan168
  1

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

  #1288 opened 22 days ago by david-sitsky
  7

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

  #1341 opened a month ago by tjinjin95
  1

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

  #1340 opened a month ago by tjinjin95
  0

• Error when attempting to optimize stable-diffusion with directML

  #1267 opened 2 months ago by fragfeaster777
  6

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

  #1327 opened a month ago by giocafe
  1

• 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 3 months ago by WA225
  14

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

  #1287 opened 2 months ago by saddam213
  4

• error while inferencing the mistral LLM

  #1309 opened 2 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 2 months ago by purejomo
  3

• Missing implementation error for CoreML

  #1299 opened 2 months ago by thewh1teagle
  1

• whisper transcriptions is empty

  #1291 opened 2 months ago by thewh1teagle
  2

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

  #1164 opened 4 months ago by peterer0625
  1

• Very slow inference of optimized whisper gpu

  #1300 opened 2 months ago by thewh1teagle
  0

• Optimize whisper medium gpu failed

  #1298 opened 2 months ago by thewh1teagle
  0

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

  #1221 opened 3 months ago by WA225
  0

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

  #1282 opened 2 months ago by yichunx1
  3

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

  #1283 opened 2 months ago by MayuraRam
  1

• Get Error while optimizing SDXL of DirectML example

  #1165 opened 4 months ago by klin2024
  1

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

  #1202 opened 3 months ago by AshD
  6

• getting error while running llama2/bert on GPU

  #1279 opened 2 months ago by himanshushukla12
  5

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

  #1251 opened 2 months ago by thevishalagarwal
  1

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

  #1170 opened 4 months ago by woonyee28
  2

• Whisper optimization using ORT toolchain

  #1264 opened 2 months ago by reeselevine
  2

• [FR]: Gather per-pass output logs

  #1269 opened 2 months ago by skywall
  2

• Whisper tool_command_args "skip_special_tokens": false config ignored

  #1274 opened 2 months ago by david-sitsky
  1

• Exporting to ONNX with kv_cache

  #1240 opened 2 months ago by idruker-cerence
  6

• nice pcode

  #1248 opened 2 months ago by chemitax202
  0

• optimizing whisper without audio_decoder

  #1236 opened 3 months ago by Aiurus
  3

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

  #1231 opened 3 months ago by MrRace
  6

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

  #1223 opened 3 months ago by xhcao
  3

• [Whisper] convert with FP32 running failed

  #1207 opened 3 months ago by Jay19751103
  4

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

  #1197 opened 4 months ago by hasayakey
  2

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

  #1186 opened 4 months ago by shaon-chowdhury
  1

• Failed to optimize Whisper tiny by gpu (CUDA)

  #1196 opened 3 months ago by XciciciX
  0

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

  #1193 opened 3 months ago by Elizabeth819
  3

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

  #1194 opened 4 months ago by hooroobaby
  0

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

  #1144 opened 5 months ago by Harini-Vemula-2382
  2

• [FR]: Finetuning QLoRA adapters and swapping

  #1182 opened 4 months ago by franperezlopez
  1

• onnx

  #1156 opened 5 months ago by xalteropsx
  0

• safetensor model

  #1153 opened 5 months ago by neonarc4
  0

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

  #1158 opened 5 months ago by neonarc4
  0

• Vitis quantization is broken with ORT 1.18

  #1125 opened 5 months ago by guotuofeng
  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 5 months ago by vijayaVTT
  2

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

  #1108 opened 5 months ago by MrRace
  1