Resources

View closed (14)

roagrawal

#34 opened about 1 month ago by

roagrawal

#33 opened about 1 month ago by

roagrawal

nvidia

#29 opened 3 months ago by

oldmonk69

Fix modeling_nemotron_h.py

#28 opened 3 months ago by

rrs1616

NVIDIA-Nemotron-Nano-9B-v2 with Docker

🤗 1

#27 opened 4 months ago by

MOHASOFT

Add Streaming Tool Calling support

#26 opened 4 months ago by

crisafullifr

What inference setting for coding?

#25 opened 4 months ago by

akierum

Can we have more detailed instructions on installing dependencies?

➕ 1

#24 opened 4 months ago by

steveheh

Update README.md

#23 opened 4 months ago by

sudoping01

Any plans to release the training recipe?

👍 👀 5

#21 opened 4 months ago by

nskwal

Request: DOI

#19 opened 5 months ago by

itsAmmar

feat: Add CPU support

#18 opened 5 months ago by

gabegoodhart

I think yall can afford to benchmark Qwen 3 8B

👍 1

#17 opened 5 months ago by

owenqwenllmwine

Slower than Qwen3-8B despite claimed 3x inference speedup

#16 opened 5 months ago by

coszeros

sad! no tool calls in streaming mode.

#15 opened 5 months ago by

j4ys0n

HybridMambaAttentionDynamicCache is not valid?

➕ 2

#14 opened 5 months ago by

GentleLiu

Any plans for MLX support?

#12 opened 5 months ago by

Alealejandrooo

some problem when I asked the model: 你是谁？

🤯 2

#8 opened 5 months ago by

wenzel94

OOM with vllm==0.10.1 on GPU L40S

#7 opened 5 months ago by

qingfu

GGUF support

❤️ 4

#4 opened 5 months ago by

RedEyed

This just trades general performance for domain specific gains.

🔥 👍 16

#3 opened 5 months ago by

phil111