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
[Misc] Fix codeowners override for v1 sample and attention (#25037)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Sep 27, 2025 at 00:47 UTC
39391520698e8b1d699ea2ccec571a6c6416ba9d
1 file changed
+5
-5
.github/CODEOWNERS
+5
-5
@@ -12,8 +12,6 @@
12
/vllm/model_executor/layers/mamba @tdoublep
13
/vllm/model_executor/model_loader @22quinn
14
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche
15
-/vllm/v1/attention @LucasWilkinson
16
-/vllm/v1/sample @22quinn @houseroad
15
/vllm/vllm_flash_attn @LucasWilkinson
16
/vllm/lora @jeejeelee
17
/vllm/reasoning @aarnphm @chaunceyjiang
@@ -28,11 +26,13 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
26
27
# vLLM V1
28
/vllm/v1 @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @comaniac @alexm-redhat
31
-/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
32
-/vllm/v1/spec_decode @benchislett @luccafong
29
+/vllm/v1/attention @LucasWilkinson
30
/vllm/v1/attention/backends/flashinfer.py @mgoin
31
/vllm/v1/attention/backends/triton_attn.py @tdoublep
32
/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @comaniac @alexm-redhat @heheda12345 @ApostaC
33
+/vllm/v1/sample @22quinn @houseroad @njhill
34
+/vllm/v1/spec_decode @benchislett @luccafong
35
+/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
36
/vllm/v1/kv_cache_interface.py @heheda12345
37
/vllm/v1/offloading @ApostaC
38
@@ -54,7 +54,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
54
/tests/weight_loading @mgoin @youkaichao @yewentao256
55
/tests/lora @jeejeelee
56
/tests/models/language/generation/test_hybrid.py @tdoublep
57
-/tests/v1/kv_connector/nixl_integration @NickLucche
57
+/tests/v1/kv_connector/nixl_integration @NickLucche
58
/tests/v1/kv_connector @ApostaC
59
/tests/v1/offloading @ApostaC
60