@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 650a4cc55e
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, 00:30 UTC

[Misc] Add transformers version to collect_env.py (#5259)

Michael Goin committed Jun 4, 2024 at 15:52 UTC 650a4cc55ef5515a14aed12ea4e069462716b2d9
1 file changed +2
collect_env.py
+2
@@ -64,6 +64,7 @@ DEFAULT_CONDA_PATTERNS = {
64 "triton",
65 "optree",
66 "nccl",
67 + "transformers",
68 }
69
70 DEFAULT_PIP_PATTERNS = {
@@ -75,6 +76,7 @@ DEFAULT_PIP_PATTERNS = {
76 "optree",
77 "onnx",
78 "nccl",
79 + "transformers",
80 }
81
82