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