AlpinDale 696f2cd59c add phi3_small support with blocksparse attention hai 6 meses
..
__init__.py 07aa2a492f upstream: add option to specify tokenizer hai 1 ano
api_server.py fe431bb840 check for next port if current is unavailable hai 6 meses
args.py 8f9cb7235c chore: allow multiple served model names hai 8 meses
protocol.py be8154a8a0 feat: proper embeddings API with e5-mistral-7b support hai 6 meses
samplers.json ac82b67f75 feat: naive context shift and various QoL changes (#289) hai 11 meses
serving_chat.py e8b7f53321 allow prompt token IDs in the logits processor api hai 6 meses
serving_completions.py be8154a8a0 feat: proper embeddings API with e5-mistral-7b support hai 6 meses
serving_embedding.py 54a4cef647 add bias and tie word embedding support for llama hai 6 meses
serving_engine.py 696f2cd59c add phi3_small support with blocksparse attention hai 6 meses