@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / fee4dcc33a
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] update collect env (#5261)

youkaichao committed Jun 4, 2024 at 15:29 UTC fee4dcc33ad3fb3988bfdf89aceef04c462ae1ce
1 file changed +5
collect_env.py
+5
@@ -603,6 +603,11 @@ Versions of relevant libraries:
603 {conda_packages}
604 """.strip()
605
606 +# both the above code and the following code use `strip()` to
607 +# remove leading/trailing whitespaces, so we need to add a newline
608 +# in between to separate the two sections
609 +env_info_fmt += "\n"
610 +
611 env_info_fmt += """
612 ROCM Version: {rocm_version}
613 Neuron SDK Version: {neuron_sdk_version}