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). @ a7d0ef69ce6dbda44ee805ff926b3c6ad26631f1

AlpinDale 89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)		пре 3 месеци
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	пре 8 месеци
batch_expansion.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
draft_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	пре 3 месеци
interfaces.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
medusa_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	пре 4 месеци
metrics.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
mlp_speculator_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
multi_step_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	пре 4 месеци
ngram_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
proposer_worker_base.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	пре 4 месеци
smaller_tp_proposer_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	пре 4 месеци
spec_decode_worker.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	пре 4 месеци
target_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	пре 3 месеци
top1_proposer.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци
util.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 4 месеци