huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Missing update after rebase

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-13 13:09:22 +00:00
parent 71a535e401
commit 3397b26341
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/models/causal_lm.py
View File

@ -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")

6
server/text_generation_server/models/seq2seq_lm.py
View File

@ -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")