# GLM-5.3 FULL EXL3 3bpw mcg — 4x DGX Spark TP=4 (+DCP=4 for 1M) — DRAFT for ~/glm53-mia/.env.tp4 on .1 # ranks: .1 head, .2 / .3 / .5 workers (all on the 10.100.10.x CX7 fabric, same NIC names) HEAD_IP=10.100.10.1 WORKER_IP=10.100.10.2 WORKER2_IP=10.100.10.3 WORKER3_IP=10.100.10.5 WORKER_USER=keyspark NCCL_CROSS_NIC=0 HEAD_CX7_IF=enp1s0f1np1 HEAD_CX7_IB=rocep1s0f1 WORKER_CX7_IF=enP2p1s0f1np1 WORKER_CX7_IB=roceP2p1s0f1 WORKER2_CX7_IF=enp1s0f1np1 WORKER2_CX7_IB=rocep1s0f1 WORKER3_CX7_IF=enp1s0f1np1 WORKER3_CX7_IB=rocep1s0f1 NCCL_IB_GID_INDEX=3 NCCL_DEBUG=WARN TP=4 NNODES=4 PORT=8888 MASTER_PORT=29521 CONTAINER_HEAD=glm53-exl3-tp4-head CONTAINER_WORKER=glm53-exl3-tp4-w1 CONTAINER_WORKER2=glm53-exl3-tp4-w2 CONTAINER_WORKER3=glm53-exl3-tp4-w3 # model: quantized on .3 -> exported over NFS as /mnt/models-node2/ on every node LOCAL_MODEL_DIR=/mnt/models-node2/GLM-5.3-EXL3-3bpw MODEL=keys/GLM-5.3-EXL3-3bpw SERVED_MODEL_NAME=GLM-5.3-EXL3 IMAGE=glm53-exl3-tp4:keys3 QUANTIZATION=exl3 KV_CACHE_DTYPE=fp8 MAX_MODEL_LEN=1000000 GPU_MEM_UTIL=0.82 MAX_NUM_SEQS=8 MAX_NUM_BATCHED_TOKENS=4096 SPEC_METHOD=mtp LANGUAGE_MODEL_ONLY=1 ENFORCE_EAGER=0 EXTRA_ARGS="--decode-context-parallel-size 4 --kv-cache-memory-bytes 14092861440" LOCAL_DFLASH_DIR=/mnt/models-node2/GLM-5.3-DFlash2 DFLASH_TOKENS=7 GLM53_MIXED_PREFILL_CHUNK=2048 MTP_TOKENS=3