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, 19:45 UTC
[Misc] Add @tomeras91 as a maintainer of Nemotron related code + mamba block (#38547)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
tomeras91 committed
Mar 30, 2026 at 16:12 UTC
246dc7d864c87f2b7eaf7ecbbd068f16e8b7a249
1 file changed
+7
-2
.github/CODEOWNERS
+7
-2
@@ -8,7 +8,7 @@
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
11
+/vllm/model_executor/layers/mamba @tdoublep @tomeras91
12
/vllm/model_executor/layers/mamba/gdn_linear_attn.py @tdoublep @ZJY0516
13
/vllm/model_executor/model_loader @22quinn
14
/vllm/model_executor/layers/batch_invariant.py @yewentao256
@@ -82,7 +82,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
82
/tests/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery
83
/tests/weight_loading @mgoin @youkaichao @yewentao256
84
/tests/lora @jeejeelee
85
-/tests/models/language/generation/test_hybrid.py @tdoublep
85
+/tests/models/language/generation/test_hybrid.py @tdoublep @tomeras91
86
/tests/v1/kv_connector/nixl_integration @NickLucche
87
/tests/v1/kv_connector @ApostaC @orozery
88
/tests/v1/kv_offload @ApostaC @orozery
@@ -126,6 +126,11 @@ mkdocs.yaml @hmellor
126
/vllm/platforms/xpu.py @jikunshang
127
/docker/Dockerfile.xpu @jikunshang
128
129
+# Nemotron-specific files
130
+/vllm/model_executor/models/*nemotron* @tomeras91
131
+/vllm/transformers_utils/configs/*nemotron* @tomeras91
132
+/tests/**/*nemotron* @tomeras91
133
+
134
# Qwen-specific files
135
/vllm/attention/backends/dual_chunk_flash_attn.py @sighingnow
136
/vllm/model_executor/models/qwen* @sighingnow