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). @ dry

AlpinDale 7a313483f1 chore: move update_flash_attn_metadata to attn backend (#731)		4 달 전
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 달 전
batch_expansion.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
draft_model_runner.py	7a313483f1 chore: move update_flash_attn_metadata to attn backend (#731)	4 달 전
interfaces.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
medusa_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 달 전
metrics.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
mlp_speculator_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
multi_step_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 달 전
ngram_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
proposer_worker_base.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 달 전
smaller_tp_proposer_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 달 전
spec_decode_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 달 전
target_model_runner.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
top1_proposer.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
util.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전