🏗️ Building on HF

Marc Sun PRO

marcsun13

huggingface

·

AI & ML interests

Open source at Hugging Face

Recent Activity

liked a Space 3 days ago

upvoted a paper 3 days ago

Harness^2: Recursive Agent Harnessing for an Open World

liked a Space 4 days ago

lerobot/steer-a-robot

View all activity

Organizations

New activity in huggingface/documentation-images about 1 month ago

Add GGUF benchmark charts

#663 opened about 1 month ago by

New activity in huggingface/documentation-images 3 months ago

nunchaku-diffusers

#647 opened 3 months ago by

New activity in kernels-community/triton_kernels about 1 year ago

Implement make_opt_flags function for XPU

#5 opened about 1 year ago by

Kernel assertion errors on 5090 using generation with MXfp4 (gpt-oss) - (stable on 4090)

#1 opened about 1 year ago by

Update torch-ext/triton_kernels/matmul_ogs_details/opt_flags.py

#3 opened about 1 year ago by

Update build/torch-universal/triton_kernels/matmul_ogs_details/opt_flags.py

#2 opened about 1 year ago by

New activity in openai/gpt-oss-20b about 1 year ago

Don't think this works on 4090 with transformers, for me anyway

#53 opened about 1 year ago by

New activity in openai/gpt-oss-120b about 1 year ago

Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b

#32 opened about 1 year ago by

running mxfp4 on H100 using tranformers with triton_kernel: make_default_matmul_mxfp4_w_layout not found

#64 opened about 1 year ago by

gpt_oss error when running on kaggle

#72 opened about 1 year ago by

New activity in openai/gpt-oss-20b about 1 year ago

Open AI open source models not able to run ...

#34 opened about 1 year ago by

RTX 5000 can't not use this model...

#41 opened about 1 year ago by

MXFP4 only runs on h100 or b100 or later versions,

#61 opened about 1 year ago by

information how to get it working on a 3090

#63 opened about 1 year ago by

how to ignore the quantization

#70 opened about 1 year ago by

New activity in openai/gpt-oss-120b about 1 year ago

OOM on 3090

#52 opened about 1 year ago by

New activity in hf-accelerate/accelerate_examples over 1 year ago

add multi_xpu configuration

#5 opened over 1 year ago by

New activity in hf-accelerate/model-memory-usage over 1 year ago

Error accessing Llama4 models: 'does not have any library metadata on the Hub'

#39 opened over 1 year ago by

GPTQ group size effects vRAM usage

#18 opened about 3 years ago by

Determining Minimum GPU Memory and Input Text Length Calculation in Model Training

#19 opened about 3 years ago by