kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
6fe89ea00f
TensorRT-LLMs/cpp/tensorrt_llm/runtime/moeLoadBalancer
History
dongxuy04 00eaf5f883
[None][feat] add flag for EPLB to force using GDRCopy (#8650) 
Signed-off-by: Dongxu Yang <78518666+dongxuy04@users.noreply.github.com>
2025-10-29 13:33:26 +08:00
..
gdrwrap.cpp [None][fix] Allow multi-threaded copy for GDRCopy wrapper (#8535) 2025-10-23 10:25:04 +08:00
gdrwrap.h feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226) 2025-06-25 22:25:13 -07:00
hostAccessibleDeviceAllocator.cpp [None][feat] add flag for EPLB to force using GDRCopy (#8650) 2025-10-29 13:33:26 +08:00
hostAccessibleDeviceAllocator.h feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226) 2025-06-25 22:25:13 -07:00
moeLoadBalancer.cpp [None][fix] Fix EPLB CPU thread NUMA binding (#8579) 2025-10-22 10:52:09 -04:00
moeLoadBalancer.h [None][fix] Fix EPLB CPU thread NUMA binding (#8579) 2025-10-22 10:52:09 -04:00
topologyDetector.cpp feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226) 2025-06-25 22:25:13 -07:00
topologyDetector.h feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226) 2025-06-25 22:25:13 -07:00