@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 86b45ae065
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 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