From 3397b26341a49d0656fbc1263c83aa99cc235e64 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Mon, 13 May 2024 13:09:22 +0000 Subject: [PATCH] Missing update after rebase --- server/text_generation_server/models/causal_lm.py | 6 +++--- server/text_generation_server/models/seq2seq_lm.py | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/server/text_generation_server/models/causal_lm.py b/server/text_generation_server/models/causal_lm.py index 93ec6ba4..81a02163 100644 --- a/server/text_generation_server/models/causal_lm.py +++ b/server/text_generation_server/models/causal_lm.py @@ -482,12 +482,12 @@ class CausalLM(Model): model_id: str, revision: Optional[str] = None, quantize: Optional[str] = None, - use_medusa: Optional[str] = None, + speculator: Optional[str] = None, dtype: Optional[torch.dtype] = None, trust_remote_code: bool = False, ): - if use_medusa: - raise RuntimeError("Medusa decoding is not enabled for AutoModel") + if speculator: + raise RuntimeError("Speculator decoding is not enabled for AutoModel") if torch.cuda.is_available(): device = torch.device("cuda") diff --git a/server/text_generation_server/models/seq2seq_lm.py b/server/text_generation_server/models/seq2seq_lm.py index e55a661c..6a0c812f 100644 --- a/server/text_generation_server/models/seq2seq_lm.py +++ b/server/text_generation_server/models/seq2seq_lm.py @@ -532,12 +532,12 @@ class Seq2SeqLM(Model): model_id: str, revision: Optional[str] = None, quantize: Optional[str] = None, - use_medusa: Optional[str] = None, + speculator: Optional[str] = None, dtype: Optional[torch.dtype] = None, trust_remote_code: bool = False, ): - if use_medusa: - raise RuntimeError("Medusa decoding is not enabled for AutoModel") + if speculator: + raise RuntimeError("Speculator decoding is not enabled for AutoModel") if torch.cuda.is_available(): device = torch.device("cuda")