mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
14 lines
748 B
JSON
14 lines
748 B
JSON
{
|
|
"Generic Runtime": ["funatiq", "pcastonguay", "Shixiaowei02", "MartinMarciniszyn", "schetlur-nv", "dcampora"],
|
|
"Triton Backend": ["Tabrizian", "pcastonguay", "schetlur-nv"],
|
|
"LLM API/Workflow": ["Superjomn", "syuoni", "nv-guomingz", "litaotju", "QiJune"],
|
|
"KV-Cache Management":["thorjohnsen", "schetlur-nv"],
|
|
"Low Precision":["Tracin", "nv-guomingz", "Naveassaf"],
|
|
"Speculative Decoding":["yweng0828", "nekorobov", "lfr-0531"],
|
|
"Customized Kernels":["lowsfer", "PerkzZheng", "jdemouth-nvidia"],
|
|
"Performance": ["kaiyux", "jiahanc", "hypdeb"],
|
|
"Lora/P-tuning":["byshiue", "Naveassaf"],
|
|
"Disaggregated Serving":["Shixiaowei02", "joyang-nv", "chuangz0", "schetlur-nv"],
|
|
"Documentation":["nv-guomingz"]
|
|
}
|