Netanel Haber

Nvidia-NetanelHaber

·

AI & ML interests

None yet

Recent Activity

new activity 19 days ago

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4:Explicitly set `VLLM_HUMMING_MOE_GEMM_TYPE=indexed` for humming, to prep for vllm main.

new activity 5 months ago

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4:Remove vLLM NVFP4 tp>1 caveat

new activity 5 months ago

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8:Remove vLLM NVFP4 tp>1 caveat

View all activity

Organizations

New activity in nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 19 days ago

Explicitly set `VLLM_HUMMING_MOE_GEMM_TYPE=indexed` for humming, to prep for vllm main.

#12 opened 19 days ago by

Nvidia-NetanelHaber

New activity in nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 5 months ago

Remove vLLM NVFP4 tp>1 caveat

#4 opened 5 months ago by

Nvidia-NetanelHaber

New activity in nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 5 months ago

Remove vLLM NVFP4 tp>1 caveat

#3 opened 5 months ago by

Nvidia-NetanelHaber

New activity in nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 5 months ago

Remove vLLM NVFP4 tp>1 caveat

#11 opened 5 months ago by

Nvidia-NetanelHaber

liked 3 models 5 months ago

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Any-to-Any • 18B • Updated Aug 24 • 626k • 194

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

Any-to-Any • 33B • Updated Aug 25 • 1.07M • 63

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

Any-to-Any • 33B • Updated Aug 24 • 367k • 434

New activity in nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 5 months ago

Fix "download the weights" rendering

#4 opened 5 months ago by

Nvidia-NetanelHaber

New activity in nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 10 months ago

Mention BF16 SGLang support

#6 opened 10 months ago by

Nvidia-NetanelHaber

Add SGLang inference commands to README

#7 opened 10 months ago by

Nvidia-NetanelHaber

Mention BF16 SGLang support

#6 opened 10 months ago by

Nvidia-NetanelHaber