Jonathan Schemoul

jon1012's activity

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

New activity in nvidia/GLM-5.3-Flash-NVFP4 2 days ago

ignore / exclude_modules omits the MTP layer (45): checkpoint fails to load with speculative decoding

❤️ 2

#6 opened 2 days ago by

jon1012

New activity in LibertAIDAI/DeepSeek-V4.1-Flash-NVFP4 3 days ago

Thank you so much for your excellent job!!!!

1

#1 opened 3 days ago by

nakululusatuva

New activity in LibertAIDAI/GLM-5.3-Flash-NVFP4 13 days ago

B200 VLLM:glm53-flash

5

#2 opened 18 days ago by

corgito

The model's single-inference speed measured on two DGX systems is only 16 tokens/s, which does not meet productivity requirements.

1

#9 opened 13 days ago by

SAJDOQPDPS

New activity in LibertAIDAI/GLM-5.3-Flash-NVFP4 14 days ago

GLM-5.3-Flash (NVFP4) on 4× DGX Spark — Multi-Node TP4 Benchmark (5.3–7.0 tok/s)

👍🔥 1

3

#5 opened 17 days ago by

tvearl

Deployment blocked: FlashInfer "Unsupported architecture" on DGX Spark (SM121)

4

#4 opened 18 days ago by

JayceHuang

Repetition

👍 1

4

#7 opened 14 days ago by

aeminkocal

GB10 tile values confirmed for DFLASH verify shape + a memory-config note for spec decoding

❤️ 1

1

#6 opened 17 days ago by

randomllama

New activity in LibertAIDAI/GLM-5.3-Flash-NVFP4 17 days ago

Is sglang supported?

1

#1 opened 18 days ago by

botian

Sm120/rtx6000pro supported?

7

#3 opened 18 days ago by

Quadrapole

New activity in LibertAIDAI/Nex-N2-mini-NVFP4-GGUF 3 months ago

great resource

1

#1 opened 3 months ago by

Hansdudin202

New activity in LibertAIDAI/Qwen3.6-27B-NVFP4-MTP-GGUF 4 months ago

can you upload your build for llama cpp for sm120 for us

1

#1 opened 4 months ago by

xueqing12

New activity in LibertAIDAI/Qwen3.6-27B-NVFP4-GGUF 4 months ago

MTP?

1

#2 opened 4 months ago by

DirkDiggler-435

Why q4 model is so small?

1

#1 opened 4 months ago by

bb2103