Jay comments

Results 17 comments of

Jay

[Devices] Offer support for hardware-accelerated inference in Firecracker

Any updates on GPU support in your roadmap for 2023/2024?

Hello, can you explain the principle of calculating distance

I think it's this: https://stackoverflow.com/a/27502480/886314

Loading pipeline components spend a lot of time

Bump Experiencing the same. Wonder what is the causing the delay Edit: probably from https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L118

SDXL support

@teftef6220 can you tell us what changes are needed? Maybe we can help

RuntimeError: cuFFT error: CUFFT_INTERNAL_ERROR

This worked for me `conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=12.1 -c pytorch -c nvidia` I have 12.1 installed so I just bumped the version

Personal Computer requirement questions

> [https://github.com/LargeWorldModel/LWM/issues/7#issuecomment-1944919388](url) fixed URL: https://github.com/LargeWorldModel/LWM/issues/7

How can the cache be disabled on yas3fs

@discreet did you try using --recheck-s3 option?

Can't find `nvidia-smi` in 2.1.4-py3-tf-gpu

I see. There was no `nvidia-smi` in that image. Looks like nvidia has not released any official docker image for debian: https://hub.docker.com/r/nvidia/cuda/tags/

Human voice activity detection (AIS-1287)

@tareqAmen you can try setting `.vad_mode = VAD_MODE_4` in afe_config_t variable. It can go from 0-4 Default is 3 and 0 is most sensitive https://github.com/espressif/esp-sr/blob/455314a90cac59d4f50253cf719659f0b9f5d778/include/esp32s3/esp_vad.h#L30

offline example doesn't recognise speech

@IVData you just have to install the package again