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 9, 10:00 UTC
[Misc] Add orozery to CODEOWNERS (core, kv_transfer, kv_offload) (#33227)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Or Ozeri committed
Jan 29, 2026 at 06:24 UTC
a663b218aefa8f807970a6cab52f9cd7f9afa011
1 file changed
+8
-6
.github/CODEOWNERS
+8
-6
@@ -16,7 +16,7 @@
16
/vllm/entrypoints @aarnphm @chaunceyjiang
17
/vllm/tool_parsers @aarnphm @chaunceyjiang
18
/vllm/compilation @zou3519 @youkaichao @ProExpertProg
19
-/vllm/distributed/kv_transfer @NickLucche @ApostaC
19
+/vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery
20
CMakeLists.txt @tlrmchlsmth @LucasWilkinson
21
22
# Any change to the VllmConfig changes can have a large user-facing impact,
@@ -30,12 +30,14 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
30
/vllm/v1/attention/backends/mla @pavanimajety
31
/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety
32
/vllm/v1/attention/backends/triton_attn.py @tdoublep
33
-/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC
33
+/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery
34
/vllm/v1/sample @22quinn @houseroad @njhill
35
/vllm/v1/spec_decode @benchislett @luccafong
36
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
37
/vllm/v1/kv_cache_interface.py @heheda12345
38
-/vllm/v1/offloading @ApostaC
38
+/vllm/v1/kv_offload @ApostaC @orozery
39
+/vllm/v1/worker/gpu/kv_connector.py @orozery
40
+/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery
41
42
# Model runner V2
43
/vllm/v1/worker/gpu @WoosukKwon
@@ -54,13 +56,13 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
56
/tests/test_inputs.py @DarkLight1337 @ywang96
57
/tests/v1/entrypoints/llm/test_struct_output_generate.py @mgoin @russellb @aarnphm
58
/tests/v1/structured_output @mgoin @russellb @aarnphm
57
-/tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC
59
+/tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery
60
/tests/weight_loading @mgoin @youkaichao @yewentao256
61
/tests/lora @jeejeelee
62
/tests/models/language/generation/test_hybrid.py @tdoublep
63
/tests/v1/kv_connector/nixl_integration @NickLucche
62
-/tests/v1/kv_connector @ApostaC
63
-/tests/v1/offloading @ApostaC
64
+/tests/v1/kv_connector @ApostaC @orozery
65
+/tests/v1/kv_offload @ApostaC @orozery
66
/tests/v1/determinism @yewentao256
67
68
# Transformers modeling backend