pathosethoslogos

pathosethoslogos's activity

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

New activity in incoai/Qwen3.8-27B-DFlash2 about 11 hours ago

When will it come to mainline vLLM Git?

#7 opened about 11 hours ago by

pathosethoslogos

New activity in unsloth/Qwen3.8-27B-NVFP4 about 13 hours ago

run on DGX SPARK

1

#23 opened 1 day ago by

Muyanghao

New activity in danish-foundation-models/DFM-Mimir 2 days ago

Is this really a 1B model?

4

#2 opened 8 days ago by

mindplay

New activity in ornith-ai/Ornith-1.5-35B-A3B 3 days ago

model-00016-of-00016.safetensors was just updated... What?

3

#25 opened 3 days ago by

pathosethoslogos

New activity in ornith-ai/Ornith-1.5-35B-A3B 5 days ago

Don't believe the benchmarks in the model card -- it fails the most basic tool calls like reading + writing files repeatedly under various settings

22

#8 opened 7 days ago by

pathosethoslogos

New activity in poolside/Laguna-S-2.1 6 days ago

</think> every response

5

#36 opened 22 days ago by

pathosethoslogos

New activity in unsloth/Qwen3.8-27B-NVFP4 6 days ago

Inferact/Qwen3.8-27B-NVFP4 is on vLLM's official documentation

9

#8 opened 12 days ago by

pathosethoslogos

New activity in RedHatAI/Qwen3.8-27B 7 days ago

The model goes crazy and goes into loops

1

#1 opened 7 days ago by

pathosethoslogos

New activity in unsloth/Qwen3.8-27B-NVFP4 7 days ago

Qwen3.8-27B Serving Configs: DGX Spark vLLM NVFP4

🤗🚀 10

6

#7 opened 12 days ago by

erdal

New activity in unsloth/Qwen3.8-27B-NVFP4 12 days ago

Does not work with vllm 0.27.1 (latest)

7

#11 opened 12 days ago by

flaviusburca

New activity in Qwen/Qwen3.8-27B 12 days ago

Bench maxed -- don't be fooled by the table presented in the model card

👀 1

4

#84 opened 12 days ago by

pathosethoslogos

New activity in Inferact/Qwen3.8-27B-NVFP4 12 days ago

unsloth/Qwen3.8-27B-NVFP4 vs. Inferact/Qwen3.8-27B-NVFP4?

🔥➕ 3

10

#1 opened 12 days ago by

pathosethoslogos

New activity in Motif-Technologies/Motif-3 12 days ago

Custom vLLM merge request to main vLLM?

👍 1

7

#6 opened 13 days ago by

pathosethoslogos

New activity in Motif-Technologies/Motif-3-NVFP4 13 days ago

Please submit a PR to vLLM for upstream model support?

👍 1

2

#2 opened 13 days ago by

GadflyII

New activity in z-lab/Qwen3.6-27B-DFlash 19 days ago

DGX Spark - 66.7% token acceptance rate - let's push it higher together

5

#19 opened about 2 months ago by

MavisFace

New activity in cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 19 days ago

Quant request

➕ 1

#7 opened 19 days ago by

pathosethoslogos

New activity in froggeric/Qwen-Fixed-Chat-Templates 4 months ago

vLLM: 'Replace the chat_template string in your tokenizer_config.json with the file contents.' ... where?

4

#5 opened 4 months ago by

pathosethoslogos

New activity in z-lab/Qwen3.6-27B-DFlash 4 months ago

Would this work with the FP8 version of the model?

4

#5 opened 4 months ago by

pathosethoslogos

New activity in deepseek-ai/DeepSeek-V4-Pro 4 months ago

I'm very disappointed in this release

🔥➕ 16

11

#131 opened 4 months ago by

Dampfinchen

New activity in sgl-project/DeepSeek-V4-Flash-FP8 4 months ago

Double the size of the original?

3

#3 opened 4 months ago by

pathosethoslogos