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). @ 561588d97d7cca90ed7fcdb936650046d0493c91

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