env_vars:
TRANSFORMERS_OFFLINE: 0 # (was 1)
. . .
RX_QUEUE_LEN: 8192
IB_RX_QUEUE_LEN: 8192
UCX_TLS: tcp
HCOLL_ENABLE_MCAST_ALL: 0
coll_hcoll_enable: 0
UCX_NET_DEVICES: ens300
NCCL_SOCKET_IFNAME: ens300
NCCL_IB_TIMEOUT: 16
NCCL_IB_SL: 0
NCCL_IB_TC: 41
NCCL_ALGO: Auto # tree, ring
NCCL_IB_GID_INDEX: 3
NCCL_IB_QPS_PER_CONNECTION: 16 # was 4
NCCL_IB_HCA: \'mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_6,mlx5_7,mlx5_8,mlx5_9,mlx5_10,mlx5_11,mlx5_12,mlx5_14,mlx5_15,mlx5_16,mlx5_17\'
NCCL_DEBUG: INFO # Logging level for NCCL. Set to "INFO" for debug information