turboderp 52e093ae6c Model: Enable max_rq_tokens (output chunking)

2025-10-05 18:54:45 +02:00

..

model.py

Model: Enable max_rq_tokens (output chunking)

2025-10-05 18:54:45 +02:00

sampler.py

Model: Add Exllamav3 sampler

2025-05-02 21:33:25 -04:00

utils.py

Model: Fix NCCL detection

2025-10-05 18:52:37 +02:00

vision.py

Exl3: Add vision capability

2025-06-15 19:22:51 +02:00