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 3, 05:30 UTC
Add dllehr-amd to CODEOWNERS and committers list (#42772)
Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com>
Douglas Lehr committed
May 20, 2026 at 16:10 UTC
452baa860b1169787cc8540a1772c4d96f682c40
2 files changed
+8
-8
.github/CODEOWNERS
+7
-7
@@ -170,13 +170,13 @@ mkdocs.yaml @hmellor
170
/vllm/model_executor/layers/fla @ZJY0516 @vadiklyutiy
171
172
# ROCm related: specify owner with write access to notify AMD folks for careful code review
173
-/vllm/**/*rocm* @tjtanaa
174
-/docker/Dockerfile.rocm* @gshtras @tjtanaa
175
-/vllm/v1/attention/backends/rocm*.py @gshtras @tjtanaa
176
-/vllm/v1/attention/backends/mla/rocm*.py @gshtras @tjtanaa
177
-/vllm/v1/attention/ops/rocm*.py @gshtras @tjtanaa
178
-/vllm/model_executor/layers/fused_moe/rocm*.py @gshtras @tjtanaa
179
-/csrc/rocm @gshtras @tjtanaa
173
+/vllm/**/*rocm* @tjtanaa @dllehr-amd
174
+/docker/Dockerfile.rocm* @tjtanaa @dllehr-amd
175
+/vllm/v1/attention/backends/rocm*.py @tjtanaa @dllehr-amd
176
+/vllm/v1/attention/backends/mla/rocm*.py @tjtanaa @dllehr-amd
177
+/vllm/v1/attention/ops/rocm*.py @tjtanaa @dllehr-amd
178
+/vllm/model_executor/layers/fused_moe/rocm*.py @tjtanaa @dllehr-amd
179
+/csrc/rocm @tjtanaa @dllehr-amd
180
/requirements/*rocm* @tjtanaa
181
/tests/**/*rocm* @tjtanaa
182
/docs/**/*rocm* @tjtanaa
docs/governance/committers.md
+1
-1
@@ -20,7 +20,7 @@ Sorted alphabetically by GitHub handle:
20
- [@chaunceyjiang](https://github.com/chaunceyjiang): Tool use and reasoning parser
21
- [@DarkLight1337](https://github.com/DarkLight1337): Multimodality, API server
22
- [@esmeetu](https://github.com/esmeetu): developer marketing, community
23
-- [@gshtras](https://github.com/gshtras): AMD integration
23
+- [@dllehr-amd](https://github.com/dllehr-amd): AMD integration
24
- [@heheda12345](https://github.com/heheda12345): Hybrid memory allocator
25
- [@hmellor](https://github.com/hmellor): Hugging Face integration, documentation
26
- [@houseroad](https://github.com/houseroad): Engine core and Llama models