Marc Sun

marcsun13's activity

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

New activity in kernels-community/triton_kernels 10 months ago

Implement make_opt_flags function for XPU

8

#5 opened 10 months ago by

YangKai0616

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

5

#1 opened 11 months ago by

cmp-nct

New activity in kernels-community/triton_kernels 11 months ago

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

#3 opened 11 months ago by

marcsun13

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

#2 opened 11 months ago by

marcsun13

New activity in openai/gpt-oss-20b 11 months ago

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

👀 2

21

#53 opened 11 months ago by

Fancellu

New activity in openai/gpt-oss-120b 11 months ago

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

🚀❤️ 19

13

#32 opened 11 months ago by

powtac

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

5

#64 opened 11 months ago by

uillliu

gpt_oss error when running on kaggle

2

#72 opened 11 months ago by

thehai

New activity in openai/gpt-oss-20b 11 months ago

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

😔 3

3

#34 opened 11 months ago by

pskmattegunta

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

👍 2

2

#41 opened 11 months ago by

arvis

MXFP4 only runs on h100 or b100 or later versions,

😔 2

12

#61 opened 11 months ago by

kishan51

information how to get it working on a 3090

👍 4

11

#63 opened 11 months ago by

TheBigBlockPC

how to ignore the quantization

❤️👍 4

3

#70 opened 11 months ago by

zzbysd

New activity in openai/gpt-oss-120b 11 months ago

OOM on 3090

4

#52 opened 11 months ago by

TheBigBlockPC

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

add multi_xpu configuration

3

#5 opened about 1 year ago by

faaany

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

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

3

#39 opened about 1 year ago by

asharma2024

GPTQ group size effects vRAM usage

2

#18 opened almost 3 years ago by

sgjohnson

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

👍 1

2

#19 opened over 2 years ago by

kobe8-24

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

#36 opened almost 2 years 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 almost 2 years ago by

AiEvanTao