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 14, 05:30 UTC
[ROCm] Starting to add AMD code reviewers for ROCm components (#23496)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Hongxia Yang committed
Aug 26, 2025 at 10:32 UTC
1fdc732419d9b9eb00e003f38d6e02c480131ac8
1 file changed
+6
.github/CODEOWNERS
+6
@@ -79,4 +79,10 @@ mkdocs.yaml @hmellor
79
/vllm/attention/ops/chunked_prefill_paged_decode.py @tdoublep
80
/vllm/attention/ops/triton_unified_attention.py @tdoublep
81
82
+# ROCm related: specify owner with write access to notify AMD folks for careful code review
83
+/docker/Dockerfile.rocm* @gshtras
84
+/vllm/v1/attention/backends/rocm*.py @gshtras
85
+/vllm/v1/attention/backends/mla/rocm*.py @gshtras
86
+/vllm/attention/ops/rocm*.py @gshtras
87
+/vllm/model_executor/layers/fused_moe/rocm*.py @gshtras
88