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 @heheda12345 to CODEOWNERS of KVCacheManager related code (#24546)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Chen Zhang committed
Sep 9, 2025 at 20:30 UTC
41f160b9741f265564c665b4a008573d9e7afc38
1 file changed
+3
.github/CODEOWNERS
+3
@@ -30,6 +30,8 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
30
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
31
/vllm/v1/spec_decode @benchislett @luccafong
32
/vllm/v1/attention/backends/triton_attn.py @tdoublep
33
+/vllm/v1/core @heheda12345
34
+/vllm/v1/kv_cache_interface.py @heheda12345
35
36
# Test ownership
37
/.buildkite/lm-eval-harness @mgoin @simon-mo
@@ -46,6 +48,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
48
/tests/test_inputs.py @DarkLight1337 @ywang96
49
/tests/v1/entrypoints/llm/test_struct_output_generate.py @mgoin @russellb @aarnphm
50
/tests/v1/structured_output @mgoin @russellb @aarnphm
51
+/tests/v1/core @heheda12345
52
/tests/weight_loading @mgoin @youkaichao @yewentao256
53
/tests/lora @jeejeelee
54
/tests/models/language/generation/test_hybrid.py @tdoublep