@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 6120e5aaea
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, 05:30 UTC

Fix import error msg for megablocks (#2038)

Woosuk Kwon committed Dec 11, 2023 at 11:40 UTC 6120e5aaeaa336a5603ff0a1e64c189624098e9a
1 file changed +4 -4
vllm/model_executor/models/mixtral.py
+4 -4
@@ -34,10 +34,10 @@ from transformers import MistralConfig
34 try:
35 import megablocks.ops as ops
36 except ImportError:
37 - print("MegaBlocks not found, please see "
38 - "https://github.com/stanford-futuredata/megablocks/. "
39 - "Note that MegaBlocks depends on mosaicml-turbo, which only "
40 - "supports python 3.10.")
37 + print(
38 + "MegaBlocks not found. Please install it by `pip install megablocks`. "
39 + "Note that MegaBlocks depends on mosaicml-turbo, which only supports "
40 + "Python 3.10 for now.")
41 try:
42 import stk
43 except ImportError: