AlpinDale 651678d2df VLM: use `SequenceData.from_token_counts` to create dummy data (#1093) пре 1 месец
..
audio 8eb4a3cfd3 vlm: support multiple audios per prompt for Ultravox (#990) пре 2 месеци
chat_templates 485d1de42e fix: hermes tool call chat template (#999) пре 2 месеци
fp8 f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
marlin 8a71788372 Add OLMoE (#772) пре 5 месеци
monitoring b26a014b12 fix: prometheus.yaml path in monitoring example (#969) пре 2 месеци
offline_inference 145e554a4d neuron: add 8bit quantization for Neuron (#994) пре 2 месеци
openai_api 313e198557 api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993) пре 2 месеци
vision 651678d2df VLM: use `SequenceData.from_token_counts` to create dummy data (#1093) пре 1 месец
aphrodite_engine_example.py f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
api_client.py f32d57ed04 add inference examples пре 1 година
gguf_to_torch.py 9d81716bfd [v0.5.3] Release Candidate (#388) пре 10 месеци
gradio_server.py e42a78381a feat: switch from pylint to ruff (#322) пре 1 година
run_cluster.sh f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
save_sharded_state.py f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
tensorize_aphrodite_model.py 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) пре 3 месеци