AlpinDale fc5ef786b0 Merge branch 'main' into lm_head_lora vor 1 Woche
..
__init__.py 07aa2a492f upstream: add option to specify tokenizer vor 1 Jahr
block.py 7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666) vor 5 Monaten
config.py fc5ef786b0 Merge branch 'main' into lm_head_lora vor 1 Woche
connections.py f1d0b77c92 [0.6.0] Release Candidate (#481) vor 5 Monaten
envs.py 9a7d5514c4 feat: introduce MQAphroditeEngine (#1056) vor 1 Monat
grammar.py 8a71788372 Add OLMoE (#772) vor 3 Monaten
logger.py 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) vor 1 Monat
logits_processor.py 8a71788372 Add OLMoE (#772) vor 3 Monaten
outputs.py 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) vor 1 Monat
pooling_params.py 2f61644f6e SPMD optimizations (#824) vor 2 Monaten
sampling_params.py f20f5c3491 samplers: improved DRY performance (#1108) vor 1 Woche
sequence.py 651678d2df VLM: use `SequenceData.from_token_counts` to create dummy data (#1093) vor 2 Wochen
test_utils.py 8a71788372 Add OLMoE (#772) vor 3 Monaten
utils.py 76088aa43a distributed: allow IPv6 in APHRODITE_HOST_IP with ZMQ (#1105) vor 2 Wochen