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). @ tools-api

AlpinDale 1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)		il y a 4 mois
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
batch_expansion.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
draft_model_runner.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
interfaces.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
medusa_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	il y a 4 mois
metrics.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
mlp_speculator_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
multi_step_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	il y a 4 mois
ngram_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
proposer_worker_base.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	il y a 4 mois
smaller_tp_proposer_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	il y a 4 mois
spec_decode_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	il y a 4 mois
target_model_runner.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
top1_proposer.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
util.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois