issues
search
EmbeddedLLM
/
vllm-rocm
vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
https://vllm.readthedocs.io
Apache License 2.0
83
stars
5
forks
source link
Checked CUDA ROCm Compatibility
#15
Closed
tjtanaa
closed
7 months ago
tjtanaa
commented
7 months ago
Feature
Auto-code path selection
support llama2
support squeezellm rocm
add documentation
amd-installation.rst
. Describing how to setup vllm ROCm version
format.sh all the code
add base amd.Dockerfile
Feature
amd-installation.rst
. Describing how to setup vllm ROCm version