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 12, 16:00 UTC
[Chore] Update batch invariant code owner (#29246)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Nov 22, 2025 at 16:50 UTC
472fdee97472cae444635508fcf73ebe28f79980
1 file changed
+2
.github/CODEOWNERS
+2
@@ -9,6 +9,7 @@
9
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety
10
/vllm/model_executor/layers/mamba @tdoublep
11
/vllm/model_executor/model_loader @22quinn
12
+/vllm/model_executor/layers/batch_invariant.py @yewentao256
13
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche @tjtanaa
14
/vllm/vllm_flash_attn @LucasWilkinson
15
/vllm/lora @jeejeelee
@@ -59,6 +60,7 @@ CMakeLists.txt @tlrmchlsmth @LucasWilkinson
60
/tests/v1/kv_connector/nixl_integration @NickLucche
61
/tests/v1/kv_connector @ApostaC
62
/tests/v1/offloading @ApostaC
63
+/tests/v1/determinism @yewentao256
64
65
# Transformers modeling backend
66
/vllm/model_executor/models/transformers @hmellor