fix: fix the ooms in gb200 default instructions (#3768)

docs/backends/sglang/dsr1-wideep-gb200.md

@@ -59,7 +59,6 @@ MC_TE_METRIC=true \
 SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE=100000 \
 SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=100000 \
 SGLANG_DISAGGREGATION_WAITING_TIMEOUT=100000 \
-SGLANG_MOONCAKE_CUSTOM_MEM_POOL=True \
 MC_FORCE_MNNVL=1 \
 NCCL_MNNVL_ENABLE=1 \
 NCCL_CUMEM_ENABLE=1 \
@@ -98,7 +97,7 @@ python3 -m dynamo.sglang \
   --disable-cuda-graph \
   --chunked-prefill-size 16384 \
   --max-total-tokens 32768 \
-  --mem-fraction-static 0.8 \
+  --mem-fraction-static 0.82 \
   --log-level debug
 ```
 
@@ -128,10 +127,10 @@ python3 -m dynamo.sglang \
   --disaggregation-mode decode \
   --dist-init-addr ${HEAD_DECODE_NODE_IP}:29500 \
   --disaggregation-bootstrap-port 30001 \
-  --nnodes 12 \
+  --nnodes 2 \
   --node-rank 0 \
-  --tp-size 48 \
-  --dp-size 48 \
+  --tp-size 8 \
+  --dp-size 8 \
   --enable-dp-attention \
   --host 0.0.0.0 \
   --decode-log-interval 1 \
@@ -155,4 +154,4 @@ python3 -m dynamo.sglang \
   --log-level debug
 ```
 
-On the other decode nodes (this example has 2 total decode nodes), run the same command but change `--node-rank` to 1
+On the other decode nodes (this example has 2 total decode nodes), run the same command but change `--node-rank` to 1.
\ No newline at end of file

docs/backends/sglang/multinode-examples.md

@@ -39,6 +39,7 @@ python3 -m dynamo.sglang \
   --disaggregation-mode prefill \
   --disaggregation-transfer-backend nixl \
   --disaggregation-bootstrap-port 30001 \
+  --load-balance-method round_robin \
   --host 0.0.0.0 \
   --mem-fraction-static 0.82
 ```
@@ -60,6 +61,7 @@ python3 -m dynamo.sglang \
   --disaggregation-transfer-backend nixl \
   --disaggregation-bootstrap-port 30001 \
   --host 0.0.0.0 \
+  --load-balance-method round_robin \
   --mem-fraction-static 0.82
 ```
 
@@ -80,6 +82,7 @@ python3 -m dynamo.sglang \
   --disaggregation-transfer-backend nixl \
   --disaggregation-bootstrap-port 30001 \
   --host 0.0.0.0 \
+  --prefill-round-robin-balance \
   --mem-fraction-static 0.82
 ```
 
@@ -100,6 +103,7 @@ python3 -m dynamo.sglang \
   --disaggregation-transfer-backend nixl \
   --disaggregation-bootstrap-port 30001 \
   --host 0.0.0.0 \
+  --prefill-round-robin-balance \
   --mem-fraction-static 0.82
 ```