david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ deepseek_v3

AlpinDale bf4a4d8516 fix: do not register punica with torch if using older torch (#948)		2 недель назад
..
ops	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	2 недель назад
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	11 месяцев назад
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 месяцев назад
layers.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 месяцев назад
lora.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 месяцев назад
models.py	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	2 недель назад
punica.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	2 недель назад
request.py	2f61644f6e SPMD optimizations (#824)	1 месяц назад
utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 месяцев назад
worker_manager.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 месяцев назад