Luke Alonso PRO

lukealonso's activity

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

New activity in canada-quant/DeepSeek-V4-Pro-NVFP4-FP8-MTP 4 days ago

Lossless?

👀 1

1

#1 opened 4 days ago by

lukealonso

New activity in lukealonso/MiMo-V2.5-NVFP4 17 days ago

Looping in OpenCode

👀 1

5

#4 opened 25 days ago by

Jon-Nielsen

New activity in lukealonso/MiMo-V2.5-NVFP4 19 days ago

The original repository has updated some files. Does this repository need to be updated?

1

#7 opened 19 days ago by

fanhed

New activity in lukealonso/MiMo-V2.5-NVFP4 20 days ago

Serving on two devices

3

#3 opened 25 days ago by

shadowlilac

Will it work on 2X6000 Pros

6

#1 opened about 1 month ago by

mtcl

Why not GGUF?

#6 opened 20 days ago by

Nerdsking

New activity in lukealonso/GLM-5.1-NVFP4 23 days ago

Quantization of the Model

1

#9 opened about 1 month ago by

shiva2022

New activity in lukealonso/MiMo-V2.5-NVFP4 26 days ago

Link to model and docker image

👍 1

1

#2 opened 26 days ago by

Jon-Nielsen

New activity in lukealonso/GLM-5.1-NVFP4 about 1 month ago

Fix tool calling: support array-formatted tool content (vLLM/SGLang)

#8 opened about 1 month ago by

cudaoom

New activity in lukealonso/MiniMax-M2.7-NVFP4 about 1 month ago

w1 not matching w3 weight scales

12

#1 opened about 2 months ago by

dareposte

tokenizer component mismatch and w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected issue

1

#5 opened about 2 months ago by

mtcl

New activity in lukealonso/GLM-5.1-NVFP4 about 2 months ago

RuntimeError: The size of tensor a (3072) must match the size of tensor b (6144) at non-singleton dimension 1

3

#5 opened about 2 months ago by

lianyouzao

From "Doesn't Work" to 641 tok/s: GLM-5.1 NVFP4 on 6× RTX PRO 6000 Blackwell

🔥 1

#4 opened about 2 months ago by

sakamakismile

Hopper GPU?

1

#2 opened about 2 months ago by

AndrewMatienko

New activity in lukealonso/MiniMax-M2.5-NVFP4 3 months ago

Request: NVFP4 version of MiniMax-M2.5-REAP-139B (to fit on a single RTX 6000 Pro)

14

#7 opened 3 months ago by

mondovero

New activity in lukealonso/GLM-5-NVFP4 3 months ago

Crash on first request on RTX Pro 6000 x8

👍 1

6

#3 opened 3 months ago by

koushd

New activity in cerebras/MiniMax-M2.5-REAP-139B-A10B 3 months ago

nvfp4

➕👍 2

1

#1 opened 3 months ago by

ktsaou

New activity in lukealonso/MiniMax-M2.5-NVFP4 3 months ago

VLLM error for kv weight scaling - workaround

7

#6 opened 3 months ago by

ShaunEvansMD

fp8 kv cache

15

#4 opened 3 months ago by

festr2

Thanks for your effort

5

#5 opened 3 months ago by

darkstar3537