Bug Casting Int8 Float Issue 15492 Microsoftonnxruntime Github
![[Bug?] Casting int8-->float · Issue #15492 · microsoft/onnxruntime · GitHub](https://user-images.githubusercontent.com/33497043/231655848-3124cc5b-5411-47d4-bfee-8b9fe978b5dc.png)
[Bug?] Casting int8-->float · Issue #15492 · microsoft/onnxruntime · GitHub
Cast Bug · Issue #8787 · microsoft/onnxruntime · GitHub
int8 poor performance · Issue #10207 · microsoft/onnxruntime · GitHub
Cast Bug · Issue #8787 · microsoft/onnxruntime · GitHub
Onnxruntime fails on GPU loading inference with int8 models · Issue ...
A bug occurs when the program terminates · Issue #15174 · microsoft ...
floating point exception · Issue #1767 · microsoft/onnxruntime · GitHub
[Performance] INT8 quantized model run slower than FP32 model · Issue ...
[BUG] GPT-j int8 requires more memory than float16 · Issue #2467 ...
BUG: StableDiffusion.inpaint() throws float tensor error · Issue #1019 ...
Advertisement Space (300x250)
A bug occurs when the program terminates · Issue #15174 · microsoft ...
![[Build] · Issue #15786 · microsoft/onnxruntime · GitHub](https://user-images.githubusercontent.com/109124994/235869968-34e097ee-a55d-403e-91ee-5852a9ba6fe1.png)
[Build] · Issue #15786 · microsoft/onnxruntime · GitHub
bug found in TensorRT when doing int8 calibration with polygraphy ...
quantize onnx models to INT8 · Issue #24374 · microsoft/onnxruntime ...
Onnxruntime fails on GPU loading inference with int8 models · Issue ...
Implicit conversion from float to int loses precision · Issue #1897 ...
Support for dynamic int8 quantization · Issue #1792 · microsoft ...
[Bug] KV cache int8 convert failed · Issue #424 · InternLM/lmdeploy ...
🐛 [Bug] Cannot export models to TensorRT with int8 quantization · Issue ...
Bug in onnxruntime\onnxruntime\core\providers\acl\nn\conv.cc? · Issue ...
Advertisement Space (336x280)
[ONNX] Float8 support · Issue #106877 · pytorch/pytorch · GitHub
[Bug]: ValueError: could not convert string to float · Issue #8317 ...
![[Training] · Issue #13824 · microsoft/onnxruntime · GitHub](https://user-images.githubusercontent.com/94303203/205343241-e14ec05b-1a75-4760-bf5e-175adaab115c.png)
[Training] · Issue #13824 · microsoft/onnxruntime · GitHub
testUsdBugs fails with float valued file truncation · Issue #2170 ...
INT8 inference with TensorRT provider · Issue #5211 · microsoft ...
README feedback · Issue #1 · microsoft/OnnxRuntime-UnrealEngine · GitHub
[Feature Request] C# Float16 DEMO, and float convert api · Issue #14303 ...
OrtGetWinMLAdapter · Issue #14954 · microsoft/onnxruntime · GitHub
Some QlinearConv can't dequantize its int8 weight with ORT1.12 · Issue ...
Bug Report: createPrefItemNumber using a Float is complicated and buggy ...
Advertisement Space (336x280)
[Bug] RTMdet onnxruntime deploy bug · Issue #1886 · open-mmlab/mmdeploy ...
[BUG] 在进行Qwen-14B量化int8时报错 · Issue #392 · QwenLM/Qwen · GitHub
8 byte Float returns 0 from FSX after upgrade to MF 9.6 · Issue #1002 ...
Bug: int8 type does not generate correctly. · Issue #54 · eProsima ...
Document that float // float returns a float · Issue #102823 · python ...
TensorRT EP failed to set INT8 dynamic range. · Issue #10206 ...