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 5, 18:30 UTC
Add @vadiklyutiy as committer (#38589)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Vadim Gimpelson committed
Mar 31, 2026 at 03:50 UTC
bb51d5b40db6076fc477df27a57e70b7421d87c1
1 file changed
+9
-8
.github/CODEOWNERS
+9
-8
@@ -2,14 +2,15 @@
2
# for more info about CODEOWNERS file
3
4
# This lists cover the "core" components of vLLM that require careful review
5
-/vllm/compilation @zou3519 @youkaichao @ProExpertProg @BoyuanFeng
5
+/vllm/compilation @zou3519 @youkaichao @ProExpertProg @BoyuanFeng @vadiklyutiy
6
/vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery
7
/vllm/lora @jeejeelee
8
/vllm/model_executor/layers/attention @LucasWilkinson @MatthewBonanni
9
/vllm/model_executor/layers/fused_moe @mgoin @pavanimajety
10
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety
11
/vllm/model_executor/layers/mamba @tdoublep @tomeras91
12
-/vllm/model_executor/layers/mamba/gdn_linear_attn.py @tdoublep @ZJY0516
12
+/vllm/model_executor/layers/mamba/gdn_linear_attn.py @tdoublep @ZJY0516 @vadiklyutiy
13
+/vllm/model_executor/layers/rotary_embedding.py @vadiklyutiy
14
/vllm/model_executor/model_loader @22quinn
15
/vllm/model_executor/layers/batch_invariant.py @yewentao256
16
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche @tjtanaa
@@ -47,9 +48,9 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
48
/vllm/v1/attention @LucasWilkinson @MatthewBonanni
49
/vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
50
/vllm/v1/attention/backends/mla @pavanimajety
50
-/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety
51
+/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety @vadiklyutiy
52
/vllm/v1/attention/backends/triton_attn.py @tdoublep
52
-/vllm/v1/attention/backends/gdn_attn.py @ZJY0516
53
+/vllm/v1/attention/backends/gdn_attn.py @ZJY0516 @vadiklyutiy
54
/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery
55
/vllm/v1/sample @22quinn @houseroad @njhill
56
/vllm/v1/spec_decode @benchislett @luccafong @MatthewBonanni
@@ -71,7 +72,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
72
/tests/distributed/test_pipeline_parallel.py @youkaichao
73
/tests/distributed/test_same_node.py @youkaichao
74
/tests/entrypoints @DarkLight1337 @robertgshaw2-redhat @aarnphm @NickLucche
74
-/tests/evals @mgoin
75
+/tests/evals @mgoin @vadiklyutiy
76
/tests/kernels @mgoin @tlrmchlsmth @WoosukKwon @yewentao256
77
/tests/models @DarkLight1337 @ywang96
78
/tests/multimodal @DarkLight1337 @ywang96 @NickLucche
@@ -132,8 +133,8 @@ mkdocs.yaml @hmellor
133
/tests/**/*nemotron* @tomeras91
134
135
# Qwen-specific files
135
-/vllm/attention/backends/dual_chunk_flash_attn.py @sighingnow
136
-/vllm/model_executor/models/qwen* @sighingnow
136
+/vllm/model_executor/models/qwen* @sighingnow @vadiklyutiy
137
+/vllm/transformers_utils/configs/qwen* @sighingnow @vadiklyutiy
138
139
# MTP-specific files
140
/vllm/model_executor/models/deepseek_mtp.py @luccafong
@@ -149,7 +150,7 @@ mkdocs.yaml @hmellor
150
# Kernels
151
/vllm/v1/attention/ops/chunked_prefill_paged_decode.py @tdoublep
152
/vllm/v1/attention/ops/triton_unified_attention.py @tdoublep
152
-/vllm/model_executor/layers/fla @ZJY0516
153
+/vllm/model_executor/layers/fla @ZJY0516 @vadiklyutiy
154
155
# ROCm related: specify owner with write access to notify AMD folks for careful code review
156
/vllm/**/*rocm* @tjtanaa