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, 23:45 UTC
[CI] Update CODEOWNERS for CPU and Intel GPU (#21582)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Jul 25, 2025 at 12:58 UTC
42343f1f89d08298addd84e7428a217b1431b56f
1 file changed
+12
.github/CODEOWNERS
+12
@@ -52,3 +52,15 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
52
# Docs
53
/docs @hmellor
54
mkdocs.yaml @hmellor
55
+
56
+# CPU
57
+/vllm/v1/worker/^cpu @bigPYJ1151
58
+/csrc/cpu @bigPYJ1151
59
+/vllm/platforms/cpu.py @bigPYJ1151
60
+/cmake/cpu_extension.cmake @bigPYJ1151
61
+/docker/Dockerfile.cpu @bigPYJ1151
62
+
63
+# Intel GPU
64
+/vllm/v1/worker/^xpu @jikunshang
65
+/vllm/platforms/xpu.py @jikunshang
66
+/docker/Dockerfile.xpu @jikunshang