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 5, 02:15 UTC
[Misc] Update `committers.md` (#40058)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Matthew Bonanni committed
Apr 16, 2026 at 16:48 UTC
219bb5b8c0dcc6a5d5f894e9168fa5b8c2f8255a
1 file changed
+6
-5
docs/governance/committers.md
+6
-5
@@ -31,6 +31,7 @@ Sorted alphabetically by GitHub handle:
31
- [@LucasWilkinson](https://github.com/LucasWilkinson): Kernels and performance
32
- [@luccafong](https://github.com/luccafong): Llama models, speculative decoding, distributed
33
- [@markmc](https://github.com/markmc): Observability
34
+- [@MatthewBonanni](https://github.com/MatthewBonanni): Kernels and performance
35
- [@mgoin](https://github.com/mgoin): Quantization and performance
36
- [@NickLucche](https://github.com/NickLucche): KV connector
37
- [@njhill](https://github.com/njhill): Distributed, API server, engine core
@@ -87,7 +88,7 @@ If you have PRs touching the area, please feel free to ping the area owner for r
88
- AsyncLLM: the zmq based protocol hosting engine core and making it accessible for entrypoints
89
- @robertgshaw2-redhat, @njhill, @russellb
90
- ModelRunner, Executor, Worker: the abstractions for engine wrapping model implementation
90
- - @WoosukKwon, @tlrmchlsmth, @heheda12345, @LucasWilkinson, @ProExpertProg
91
+ - @WoosukKwon, @tlrmchlsmth, @heheda12345, @LucasWilkinson, @ProExpertProg, @MatthewBonanni
92
- KV Connector: Connector interface and implementation for KV cache offload and transfer
93
- @robertgshaw2-redhat, @njhill, @KuntaiDu, @NickLucche, @ApostaC
94
- Distributed, Parallelism, Process Management: Process launchers managing each worker, and assign them to the right DP/TP/PP/EP ranks
@@ -106,7 +107,7 @@ If you have PRs touching the area, please feel free to ping the area owner for r
107
- Custom Layers: Utility layers in vLLM such as rotary embedding and rms norms
108
- @ProExpertProg
109
- Attention: Attention interface for paged attention
109
- - @WoosukKwon, @LucasWilkinson, @heheda12345
110
+ - @WoosukKwon, @LucasWilkinson, @heheda12345, @MatthewBonanni
111
- FusedMoE: FusedMoE kernel, Modular kernel framework, EPLB
112
- @tlrmchlsmth
113
- Quantization: Various quantization config, weight loading, and kernel.
@@ -134,7 +135,7 @@ If you have PRs touching the area, please feel free to ping the area owner for r
135
### Features
136
137
- Spec Decode: Covers model definition, attention, sampler, and scheduler related to n-grams, EAGLE, and MTP.
137
- - @WoosukKwon, @benchislett, @luccafong
138
+ - @WoosukKwon, @benchislett, @luccafong, @MatthewBonanni
139
- Structured Output: The structured output implementation
140
- @russellb, @aarnphm
141
- RL: The RL related features such as collective rpc, sleep mode, etc.
@@ -154,8 +155,8 @@ If you have PRs touching the area, please feel free to ping the area owner for r
155
156
### External Kernels Integration
157
157
-- FlashAttention: @LucasWilkinson
158
-- FlashInfer: @LucasWilkinson, @mgoin, @WoosukKwon
158
+- FlashAttention: @LucasWilkinson, @MatthewBonanni
159
+- FlashInfer: @LucasWilkinson, @mgoin, @WoosukKwon, @MatthewBonanni
160
- Blackwell Kernels: @mgoin, @yewentao256
161
- DeepEP/DeepGEMM: @mgoin, @yewentao256
162