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 4, 01:15 UTC
Add @Harry-Chen in CODEOWNERS (#42130)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Shengqi Chen committed
May 9, 2026 at 12:08 UTC
97cc7685c4866cce51aeb59b1fff5466ca6f7c2a
1 file changed
+6
-1
.github/CODEOWNERS
+6
-1
@@ -18,7 +18,8 @@
18
/vllm/kernels/helion @ProExpertProg @zou3519
19
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche @tjtanaa
20
/vllm/vllm_flash_attn @LucasWilkinson @MatthewBonanni
21
-CMakeLists.txt @tlrmchlsmth @LucasWilkinson
21
+/CMakeLists.txt @tlrmchlsmth @LucasWilkinson @Harry-Chen
22
+/cmake @tlrmchlsmth @LucasWilkinson @Harry-Chen
23
24
# Any change to the VllmConfig changes can have a large user-facing impact,
25
# so spam a lot of people
@@ -70,6 +71,10 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
71
/vllm/v1/worker/gpu @WoosukKwon @njhill
72
/vllm/v1/worker/gpu/kv_connector.py @orozery
73
74
+# CI & building
75
+/.buildkite @Harry-Chen
76
+/docker/Dockerfile @Harry-Chen
77
+
78
# Test ownership
79
/.buildkite/lm-eval-harness @mgoin
80
/tests/distributed/test_multi_node_assignment.py @youkaichao