GadflyII

GadflyII's activity

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

New activity in Motif-Technologies/Motif-3 2 months ago

Custom vLLM merge request to main vLLM?

👍 1

7

#6 opened 2 months ago by

pathosethoslogos

New activity in Motif-Technologies/Motif-3-NVFP4 2 months ago

Please submit a PR to vLLM for upstream model support?

👍 1

2

#2 opened 2 months ago by

GadflyII

New activity in GadflyII/GLM-4.6V-NVFP4 6 months ago

Well done nvfp4 quant

3

#1 opened 9 months ago by

josephbreda

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 6 months ago

Why Your NVFP4 Model Is Slower Than FP8 on the GB10 (NVIDIA Spark) — And How to Fix It

🤯👍 5

6

#5 opened 8 months ago by

scottgl

New activity in GadflyII/GLM-4.7-Flash-MTP-NVFP4 7 months ago

SGLang and MTP

1

#2 opened 8 months ago by

Michalea

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 8 months ago

Model requests?

12

#4 opened 8 months ago by

pathosethoslogos

New activity in GadflyII/GLM-4.6V-NVFP4 8 months ago

Fails on a single DGX spark with errors below

1

#2 opened 8 months ago by

Adrian1234

New activity in GadflyII/GLM-4.7-Flash-MXFP4 8 months ago

Update MXFP4 format to compressed-tensors

1

#3 opened 8 months ago by

mgoin

New activity in lukealonso/MiniMax-M2.5-NVFP4 8 months ago

Here's the vLLM recipe I'm using with 2x RTX Pro 6000

👍 3

17

#1 opened 8 months ago by

zenmagnets

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 8 months ago

MMLU PRO Benchmark

3

#3 opened 8 months ago by

sevapru

vLLM 0.16?

1

#2 opened 9 months ago by

MMaxHugg

New activity in GadflyII/Qwen3-Coder-Next-NVFP4 9 months ago

Memory

1

#1 opened 9 months ago by

struxx

New activity in GadflyII/GLM-4.7-Flash-NVFP4 9 months ago

confused response

7

#8 opened 9 months ago by

jiangyizhi

MTP quality, 47 layer

3

#7 opened 9 months ago by

Michalea

New activity in GadflyII/GLM-4.7-Flash-MTP-NVFP4 9 months ago

Upload folder using huggingface_hub

#1 opened 9 months ago by

GadflyII

New activity in GadflyII/GLM-4.7-Flash-NVFP4 9 months ago

Can't deploy by vllm 0.14.1 + transformers

8

#6 opened 9 months ago by

Butterfly-314

New activity in GadflyII/GLM-4.7-Flash-MXFP4 9 months ago

can not run

4

#1 opened 9 months ago by

aliez-ren

New activity in GadflyII/GLM-4.7-Flash-NVFP4 9 months ago

please create mlx version of this

3

#4 opened 9 months ago by

Narutoouz

Wasn't able to recreate MMLU-Pro benchmarks

5

#5 opened 9 months ago by

zenmagnets

New activity in GadflyII/MiniMax-M2.1-NVFP4 9 months ago

Request for GLM 4.6V

3

#1 opened 10 months ago by

SFPLM