@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 9974fca047
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 04:30 UTC

[ci/build] Fix entrypoints test and pin outlines version (#11088)

Kevin H. Luu committed Dec 11, 2024 at 01:01 UTC 9974fca047bb332ec68377be4579ea515a300d69
2 files changed +2 -2
requirements-common.txt
+1 -1
@@ -18,7 +18,7 @@ prometheus_client >= 0.18.0
18 prometheus-fastapi-instrumentator >= 7.0.0
19 tiktoken >= 0.6.0 # Required for DBRX tokenizer
20 lm-format-enforcer >= 0.10.9, < 0.11
21 -outlines >= 0.1.8
21 +outlines == 0.1.9
22 xgrammar >= 0.1.6; platform_machine == "x86_64"
23 typing_extensions >= 4.10
24 filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
vllm/model_executor/guided_decoding/outlines_logits_processors.py
+1 -1
@@ -25,7 +25,7 @@ from lark import Lark
25 from outlines import grammars
26 from outlines.caching import cache
27 from outlines.fsm.guide import CFGGuide, Generate, Guide, RegexGuide, Write
28 -from outlines.fsm.json_schema import build_regex_from_schema
28 +from outlines_core.fsm.json_schema import build_regex_from_schema
29 from pydantic import BaseModel
30 from transformers import PreTrainedTokenizerBase
31