Marc Sun

marcsun13's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in kernels-community/triton_kernels 4 days ago

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

2

#1 opened 10 days ago by

cmp-nct

New activity in jxm/gpt-oss-20b-base 4 days ago

Update config.json

1

#6 opened 4 days ago by

marcsun13

New activity in openai/gpt-oss-20b 16 days ago

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

👀 2

18

#53 opened 18 days ago by

Fancellu

New activity in openai/gpt-oss-120b 17 days ago

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

❤️ 🚀 12

12

#32 opened 19 days ago by

powtac

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

5

#64 opened 18 days ago by

uillliu

gpt_oss error when running on kaggle

2

#72 opened 17 days ago by

thehai

New activity in openai/gpt-oss-20b 17 days ago

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

😔 3

3

#34 opened 19 days ago by

pskmattegunta

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

👍 2

2

#41 opened 18 days ago by

arvis

MXFP4 only runs on h100 or b100 or later versions,

😔 2

11

#61 opened 18 days ago by

kishan51

information how to get it working on a 3090

👍 4

11

#63 opened 18 days ago by

TheBigBlockPC

how to ignore the quantization

❤️ 👍 4

3

#70 opened 17 days ago by

zzbysd

New activity in openai/gpt-oss-120b 18 days ago

OOM on 3090

4

#52 opened 18 days ago by

TheBigBlockPC

New activity in hf-accelerate/accelerate_examples 3 months ago

add multi_xpu configuration

3

#5 opened 3 months ago by

faaany

New activity in hf-accelerate/model-memory-usage 4 months ago

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

3

#39 opened 4 months ago by

asharma2024

GPTQ group size effects vRAM usage

2

#18 opened almost 2 years ago by

sgjohnson

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

👍 1

2

#19 opened almost 2 years ago by

kobe8-24

microsoft/Florence-2-base raises error without any detail

#36 opened 11 months ago by

fcakyon

For Llama-2 model, I tried to get the memory usage, it says I do not have the access

1

#35 opened 12 months ago by

AiEvanTao

Improve name of the model detection to allow several URL usages

2

#28 opened over 1 year ago by

Pablohn26

meta-llama/Meta-Llama-3.1-8B-Instruct ....why not found this

➕ 6

#34 opened 12 months ago by

world-of-ai