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, 22:35 UTC
Add @sighingnow as maintainer of qwen's related files. (#21895)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Tao He committed
Jul 30, 2025 at 12:30 UTC
e3bc17ceead9af80851b61a65010613eb34511e8
1 file changed
+4
.github/CODEOWNERS
+4
@@ -61,3 +61,7 @@ mkdocs.yaml @hmellor
61
/vllm/v1/worker/^xpu @jikunshang
62
/vllm/platforms/xpu.py @jikunshang
63
/docker/Dockerfile.xpu @jikunshang
64
+
65
+# Qwen-specific files
66
+/vllm/attention/backends/dual_chunk_flash_attn.py @sighingnow
67
+/vllm/model_executor/models/qwen* @sighingnow