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). @ rejection_sampling_kernels

AlpinDale 0dfa6b60ec core: support logprobs with multi-step scheduling (#963)		hace 1 mes
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	hace 8 meses
batch_expansion.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
draft_model_runner.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
interfaces.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 4 meses
medusa_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
metrics.py	2f61644f6e SPMD optimizations (#824)	hace 2 meses
mlp_speculator_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
multi_step_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
ngram_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
proposer_worker_base.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
smaller_tp_proposer_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
spec_decode_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
target_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hace 4 meses
top1_proposer.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes
util.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	hace 1 mes