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
Updated CODEOWNERS for flashinfer, mla, fused_moe (#24906)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Sep 15, 2025 at 22:01 UTC
e95084308b2032748e226f420e93becaf3af64d5
1 file changed
+7
-2
.github/CODEOWNERS
+7
-2
@@ -2,17 +2,20 @@
2
# for more info about CODEOWNERS file
3
4
# This lists cover the "core" components of vLLM that require careful review
5
+/vllm/attention @LucasWilkinson
6
/vllm/attention/backends/abstract.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
7
/vllm/core @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
8
/vllm/engine/llm_engine.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
9
/vllm/executor/executor_base.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill @22quinn
10
/vllm/worker/worker_base.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill @22quinn
11
/vllm/worker/worker.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill
12
+/vllm/model_executor/layers/fused_moe @mgoin
13
/vllm/model_executor/layers/sampler.py @zhuohan123 @youkaichao @alexm-redhat @comaniac @njhill @NickLucche
14
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256
15
/vllm/model_executor/layers/mamba @tdoublep
16
/vllm/model_executor/model_loader @22quinn
17
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche
18
+/vllm/v1/attention @LucasWilkinson
19
/vllm/v1/sample @22quinn @houseroad
20
/vllm/vllm_flash_attn @LucasWilkinson
21
/vllm/lora @jeejeelee
@@ -30,6 +33,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
33
/vllm/v1 @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @comaniac @alexm-redhat
34
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
35
/vllm/v1/spec_decode @benchislett @luccafong
36
+/vllm/v1/attention/backends/flashinfer.py @mgoin
37
/vllm/v1/attention/backends/triton_attn.py @tdoublep
38
/vllm/v1/core @heheda12345
39
/vllm/v1/kv_cache_interface.py @heheda12345
@@ -41,7 +45,8 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
45
/tests/distributed/test_pipeline_parallel.py @youkaichao
46
/tests/distributed/test_same_node.py @youkaichao
47
/tests/entrypoints @DarkLight1337 @robertgshaw2-redhat @simon-mo @aarnphm @NickLucche
44
-/tests/kernels @tlrmchlsmth @WoosukKwon @yewentao256
48
+/tests/evals @mgoin
49
+/tests/kernels @mgoin @tlrmchlsmth @WoosukKwon @yewentao256
50
/tests/models @DarkLight1337 @ywang96
51
/tests/multimodal @DarkLight1337 @ywang96 @NickLucche
52
/tests/prefix_caching @comaniac @KuntaiDu
@@ -104,4 +109,4 @@ mkdocs.yaml @hmellor
109
/vllm/tests/v1/tpu @NickLucche
110
111
# KVConnector installation files
107
-/requirements/kv_connectors.txt @NickLucche
\ No newline at end of file
112
+/requirements/kv_connectors.txt @NickLucche