🔄 In a Training Loop

Reto PRO

retowyss

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

mistralai/Mistral-Large-4-1T-A52B

liked a model about 1 month ago

local-inference-lab/Qwen3.8-Flash-Next-NVFP4

published a model 3 months ago

retowyss/gemma-4-26B-A4B-it-REAP2D

View all activity

Organizations

New activity in CohereLabs/command-a-plus-05-2026-w4a4 5 months ago

Tool calls fail in opencode

#3 opened 6 months ago by

New activity in CohereLabs/command-a-plus-05-2026-w4a4 6 months ago

Adjust context size

#1 opened 6 months ago by

New activity in deepseek-ai/DeepSeek-V4-Flash 6 months ago

Unable to run on 2x RTX Pro 6000 (DEEP_GEMM problem)

#15 opened 7 months ago by

New activity in mistralai/Mistral-Medium-3.5-128B 6 months ago

nvfp4?

#21 opened 6 months ago by

vllm-nightly kv-cache calculation seems to be off

#7 opened 7 months ago by

IndexError: list index out of range

#19 opened 6 months ago by

New activity in atbender/Qwen3.5-REAP-262B-A17B-W4A16 8 months ago

Remove unnecessary parts in docker compose for 2x Pro 6k

#6 opened 8 months ago by

Thanks for this - but I needed some patches.

#1 opened 8 months ago by

Updated patch version name in docker compose

#5 opened 8 months ago by

Docker Compose for 2x RTX Pro 6000 and notes for patch_vllm_260320.py

#4 opened 8 months ago by

Create patch_vllm_260320.py

#3 opened 8 months ago by

Create patch_vllm_2.py

#2 opened 8 months ago by

New activity in Qwen/Qwen3.5-122B-A10B 9 months ago

Official FP8

#4 opened 9 months ago by

New activity in retowyss/img-bucket 11 months ago

Upload 5 files

#1 opened 11 months ago by

New activity in Photoroom/prx-1024-t2i-beta 12 months ago

fix code snipped - import torch

#4 opened 12 months ago by