Abdennacer Badaoui

badaoui's activity

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

liked a Space 1 day ago

Running

3

Beam on AMD

🟢

3

Beam 501B on AMD MI300X, MXFP4 on 2 GPUs, pruned on 1

liked a model 6 days ago

zouaynib/Beam-1.0-501B-A23B-MXFP4

Text Generation • 255B • Updated 2 days ago • 236 • 2

upvoted an article 15 days ago

view article

Article

Sort your prompts: a free speed-up for MoE batch inference

• 

badaoui

•

15 days ago

• 10

published an article 15 days ago

view article

Article

Sort your prompts: a free speed-up for MoE batch inference

• 

badaoui

•

15 days ago

• 10

upvoted an article 19 days ago

view article

Article

Tokenmaxxing BERT: 50x faster tokenization

• 

huggingface

•

19 days ago

• 53

upvoted an article 20 days ago

view article

Article

GLM 5.3 Flash on AMD MI300X in Microsoft Foundry

• 

pagezyhf

•

20 days ago

• 6

liked a model 22 days ago

autotrust/JEV-27B-VL

Image-Text-to-Text • 28B • Updated 20 days ago • 1.93M • 3.07k

New activity in transformers-community/transformers-ci-dashboard 28 days ago

Include NVIDIA flash attention CI results in NVIDIA numbers

#17 opened 28 days ago by

badaoui

New activity in transformers-community/transformers-ci-dashboard about 1 month ago

Revert "Show overall failure rates with two decimals (#15)"

#16 opened about 1 month ago by

badaoui

Show overall failure rates with two decimals

#15 opened about 1 month ago by

badaoui

Show last real data instead of sample data when loading fails

#14 opened about 1 month ago by

badaoui

upvoted an article about 1 month ago

view article

Article

Transformers now runs llama.cpp quants

• 
• 
• +1

marcsun13, ArthurZ, lysandre

•

Sep 22

• 122

upvoted an article about 2 months ago

view article

Article

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

• 
• 
• +2

aminediroHF, qgallouedec, kashif, sergiopaniego

•

Sep 10

• 54

updated 2 Spaces about 2 months ago

Running

Agents

22

Transformers CI dashboard

👁

22

Track the transformers CI across GPUs

Running

1

Strix Halo on Transformers

⏱

1

Transformers CI on AMD Strix Halo — FA vs no-FA

liked a Space about 2 months ago

Running

Featured

780

Microduck Sandbox

🐤

780

Show a bold title with a comic‑style button

liked 2 models 3 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 8.01M • • 19.1k

deepseek-ai/DeepSeek-V4-Pro-0813

Text Generation • 1.7T • Updated Aug 13 • 152k • • 909

upvoted a collection 3 months ago

Muse Glimmer

Collection

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated Aug 10 • 129

liked a model 3 months ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 6.34M • • 6.54k