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 7, 14:00 UTC
[Misc] Fill in some v1 CODEOWNERS gaps (#35524)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Nick Hill committed
Feb 27, 2026 at 09:34 UTC
1d897ff04f90c46041ed3966dea671a6ae532184
1 file changed
+5
-2
.github/CODEOWNERS
+5
-2
@@ -54,11 +54,14 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
54
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
55
/vllm/v1/kv_cache_interface.py @heheda12345
56
/vllm/v1/kv_offload @ApostaC @orozery
57
-/vllm/v1/worker/gpu/kv_connector.py @orozery
57
+/vllm/v1/engine @njhill
58
+/vllm/v1/executor @njhill
59
+/vllm/v1/worker @njhill
60
/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery @NickLucche
61
62
# Model runner V2
61
-/vllm/v1/worker/gpu @WoosukKwon
63
+/vllm/v1/worker/gpu @WoosukKwon @njhill
64
+/vllm/v1/worker/gpu/kv_connector.py @orozery
65
66
# Test ownership
67
/.buildkite/lm-eval-harness @mgoin