Files
Enwei Zhu 205c53c447 Initial Release
Co-creators. Enwei Zhu, Jiying Dong, Xipeng Li (NVIDIA) · Pengzhan Zhao, Kyle Wang, Lei Zhang (AMD) · Jiandong Jiang, Tuan Zhang, Minmin Sun (Qwen) · Jue Wang, Yineng Zhang (Together AI) · Hongtao Chen, Mingxing Zhang (Mooncake) · Bo Wang, Fengcun Li (LongCat) · Xiangyang Ji, Yulei Qian (FluentLLM).

Core runtime. Scheduler — Yulei Qian, Fengcun Li, Bo Wang. Kernels — Lei Zhang, Pengzhan Zhao, Kyle Wang. Modeling — Yulei Qian, Xiangyang Ji, Jue Wang. MLA — Albert Di, Jiying Dong. Grammar and sampling — Jue Wang, Weicong Wu. MoE — Hongtao Chen. VLM — Hongtao Chen, Fengcun Li, Bo Wang.

Model optimization. Kimi K2.5 speed-of-light optimization — Enwei Zhu, Jiying Dong, Yue Weng, Albert Di. Qwen 3.6 — Minmin Sun, Tuan Zhang, Jiandong Jiang. DeepSeek V4 — Jiying Dong, Qingquan Song, Qiukai Chen, Yechan Kim, Hejian Sang. GPT-OSS on AMD — Pengzhan Zhao, Kyle Wang. Minimax M2.7 — Fan Yin, Jue Wang.

System and integration. Distributed runtime — Xuchun Shang, Teng Ma. Speculative decoding — Yue Weng. AsyncLLM and SMG — Simo Lin, Keyang Ru, Xipeng Guan. TensorRT-LLM kernels — Aaron Liu, Enwei Zhu. Metrics — Fred Wang. EvalScope benchmark — Xingjun Wang, Yunlin Mao. Dynamo integration — Yuewei Na, William Arnold.

Co-authored-by: aaronliuls <270489959+aaronliuls@users.noreply.github.com>
Co-authored-by: Chen Hongtao <56470055+chenht2022@users.noreply.github.com>
Co-authored-by: dongjiyingdjy <87510204+dongjiyingdjy@users.noreply.github.com>
Co-authored-by: Fan Yin <32722923+FlamingoPg@users.noreply.github.com>
Co-authored-by: Jue Wang <20911161+LorrinWWW@users.noreply.github.com>
Co-authored-by: Keyang Ru <16893865+key4ng@users.noreply.github.com>
Co-authored-by: Kyle Wang <26247277+knwng@users.noreply.github.com>
Co-authored-by: Lei Zhang <487928+antiagainst@users.noreply.github.com>
Co-authored-by: minedec <37043133+minedec@users.noreply.github.com>
Co-authored-by: Pengzhan Zhao <25846776+borontion@users.noreply.github.com>
Co-authored-by: qingquan-collab <279097144+qingquan-collab@users.noreply.github.com>
Co-authored-by: Shengbin <3850696+dishengbin@users.noreply.github.com>
Co-authored-by: Simon_CQK <19202395+SimonCqk@users.noreply.github.com>
Co-authored-by: Simo Lin <25425177+slin1237@users.noreply.github.com>
Co-authored-by: tuanzhangCS <26617745+tuanzhangCS@users.noreply.github.com>
Co-authored-by: WangBo <259098089+wangbo981016@users.noreply.github.com>
Co-authored-by: wtsung <46099630+wtsung@users.noreply.github.com>
Co-authored-by: Xiangyang Ji <19466102+woodyji@users.noreply.github.com>
Co-authored-by: Xuchun Shang <107600043+XucSh@users.noreply.github.com>
Co-authored-by: Yineng Zhang <46627482+zhyncs@users.noreply.github.com>
Co-authored-by: yetone <1206493+yetone@users.noreply.github.com>
Co-authored-by: YueWeng <25103990+yweng0828@users.noreply.github.com>
2026-05-06 13:27:02 +00:00

4 lines
54 B
INI

[settings]
profile=black
known_first_party=tokenspeed