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 17, 01:45 UTC
[Bugfix] Relax tiktoken to >= 0.6.0 (#4890)
Michael Goin committed
May 17, 2024 at 14:58 UTC
86b45ae065e8c5e4a5f2af3ee1dc19a261c58775
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -14,7 +14,7 @@ uvicorn[standard]
14
pydantic >= 2.0 # Required for OpenAI server.
15
prometheus_client >= 0.18.0
16
prometheus-fastapi-instrumentator >= 7.0.0
17
-tiktoken == 0.6.0 # Required for DBRX tokenizer
17
+tiktoken >= 0.6.0 # Required for DBRX tokenizer
18
lm-format-enforcer == 0.10.1
19
outlines == 0.0.34 # Requires torch >= 2.1.0
20
typing_extensions