-
Using Fake Tensors
-
Please see the discussion originally posted here for the technical details: https://github.com/KhronosGroup/MoltenVK/discussions/1496
In short:
```glsl
vec3 colors[3] = vec3[](
vec3(1.0, 0.…
-
Hello,
I have tried to make a simple POST call using the URL "http://127.0.0.1:5272/v1/chat/completions" , and the body as follows,
{
"model": "Phi-3-mini-128k-cuda-int4-onnx",
"messa…
-
Thanks for your exciting work!
I try to use `eval/vcgbench/inference/run_ddp_inference.sh` to reproduce the performance on VCGBench with 4*A100 GPUs, but the generated texts are garbled as follows:…
-
When I want to load .gguf model, I have this error
-
**Describe the bug**
Using mlx_lm I made a fine tuned model from `microsoft/Phi-3-mini-128k-instruct`.
Training was all fine. AFter it, when I test the tuned model with `generate` I noticed one issu…
-
### What is the issue?
(Pythogora) developer@ai:~/PROJECTS/gpt-pilot/pilot$ ~/ollama/ollama list
NAME ID SIZE MODIFIED
Meta-Llama-3-70B-…
-
System: LicheePi4A , XuanTie C910/TH1520
OS: Linux Debian
Model used phi3 - cpu and mobile - acc level 4 (from huggingface)
Python3.11 - onnxruntime version 1.19.0 - onnxruntime_genai version 0.…
-
### System Info
I meet this error when start LoraX with model `microsoft/Phi-3-mini-128k-instruct`
```
{"timestamp":"2024-05-22T07:01:39.860359Z","level":"ERROR","fields":{"message":"Shard complete…
-
I was experimenting some things with gaianet custom nodes and wanted to just test how embedding works and work with custom data for same I created a snapshot following [documentation](https://docs.gai…