Triton CLI is an open source command line interface that enables users to create, deploy, and profile models served by the Triton Inference Server.
48
stars
2
forks
source link
Add --backend support to bench command and default to custom image #27
Closed
rmccorm4 closed 8 months ago
Docker Changes
subprocess
fordocker pull
- adds simpler progress for pulling images as expected:docker build
support, along with a custom Dockerfile with both vLLM and TRT-LLM dependencies that will be built/used by default."bench" command changes
Add and passthrough
--backend
. ex:triton bench -m gpt2 --backend tensorrtllm
Add progress bars to "warming up..." and "profiling..." in profiler
Fix "trtllm" -> "tensorrtllm" backend check in profiler
TRT-LLM changes
mpirun
forworld_size==1
mpirun
seems to hide/obscure errors when they occuredmpirun
is necessary for world size of 1, but it doesn't currently appear so