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
Add @luccafong to codeowner for spec decode (#24397)
Signed-off-by: Lu Fang <fanglu@fb.com>
Lucia Fang committed
Sep 7, 2025 at 17:30 UTC
795b6951cd6a18c2d78bcb1d188f112357d19262
1 file changed
+4
-1
.github/CODEOWNERS
+4
-1
@@ -28,7 +28,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
28
# vLLM V1
29
/vllm/v1 @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @comaniac @alexm-redhat
30
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
31
-/vllm/v1/spec_decode @benchislett
31
+/vllm/v1/spec_decode @benchislett @luccafong
32
/vllm/v1/attention/backends/triton_attn.py @tdoublep
33
34
# Test ownership
@@ -70,6 +70,9 @@ mkdocs.yaml @hmellor
70
/vllm/attention/backends/dual_chunk_flash_attn.py @sighingnow
71
/vllm/model_executor/models/qwen* @sighingnow
72
73
+# MTP-specific files
74
+/vllm/model_executor/models/deepseek_mtp.py @luccafong
75
+
76
# Mistral-specific files
77
/vllm/model_executor/models/mistral*.py @patrickvonplaten
78
/vllm/model_executor/models/mixtral*.py @patrickvonplaten