diff --git a/docs/source/tutorials/pd_colocated_mooncake_multi_instance.md b/docs/source/tutorials/pd_colocated_mooncake_multi_instance.md index 4319e2d1..c6983779 100644 --- a/docs/source/tutorials/pd_colocated_mooncake_multi_instance.md +++ b/docs/source/tutorials/pd_colocated_mooncake_multi_instance.md @@ -44,7 +44,7 @@ such as IP addresses according to your actual environment. for i in {0..7}; do hccn_tool -i $i -gateway -g ; done ``` -2. Check NPU Network Configuration: +2. Check NPU HCCN Configuration: Ensure that the hccn.conf file exists in the environment. If using Docker, mount it into the container. @@ -67,6 +67,13 @@ such as IP addresses according to your actual environment. for i in {0..7}; do hccn_tool -i $i -ping -g address x.x.x.x; done ``` +5. Check NPU TLS Configuration + + ```bash + # The tls settings should be consistent across all nodes + for i in {0..7}; do hccn_tool -i $i -tls -g ; done | grep switch + ``` + ## Run with Docker Start a Docker container on each node. diff --git a/docs/source/tutorials/pd_disaggregation_mooncake_multi_node.md b/docs/source/tutorials/pd_disaggregation_mooncake_multi_node.md index 6a1dc74a..a5a060c6 100644 --- a/docs/source/tutorials/pd_disaggregation_mooncake_multi_node.md +++ b/docs/source/tutorials/pd_disaggregation_mooncake_multi_node.md @@ -37,7 +37,7 @@ for i in {0..15}; do hccn_tool -i $i -netdetect -g ; done for i in {0..15}; do hccn_tool -i $i -gateway -g ; done ``` -2. Check NPU network configuration: +2. Check NPU HCCN Configuration: Ensure that the hccn.conf file exists in the environment. If using Docker, mount it into the container. @@ -48,14 +48,28 @@ cat /etc/hccn.conf 3. Get NPU IP Addresses ```bash -for i in {0..15}; do hccn_tool -i $i -ip -g | grep ipaddr; done +# Get virtual npu ip +for i in {0..15}; do hccn_tool -i $i -vnic -g;done ``` -4. Cross-Node PING Test +4. Get superpodid and SDID ```bash -# Execute on the target node (replace 'x.x.x.x' with actual npu ip address) -for i in {0..15}; do hccn_tool -i $i -ping -g address x.x.x.x;done +for i in {0..15}; do npu-smi info -t spod-info -i $i -c 0;npu-smi info -t spod-info -i $i -c 1;done +``` + +5. Cross-Node PING Test + +```bash +# Execute on the target node (replace 'x.x.x.x' with virtual npu ip address) +for i in {0..15}; do hccn_tool -i $i -hccs_ping -g address x.x.x.x;done +``` + +6. Check NPU TLS Configuration + +```bash +# The tls settings should be consistent across all nodes +for i in {0..15}; do hccn_tool -i $i -tls -g ; done | grep switch ``` :::: @@ -79,7 +93,7 @@ for i in {0..7}; do hccn_tool -i $i -netdetect -g ; done for i in {0..7}; do hccn_tool -i $i -gateway -g ; done ``` -2. Check NPU network configuration: +2. Check NPU HCCN Configuration: Ensure that the hccn.conf file exists in the environment. If using Docker, mount it into the container. @@ -100,6 +114,13 @@ for i in {0..7}; do hccn_tool -i $i -ip -g;done for i in {0..7}; do hccn_tool -i $i -ping -g address x.x.x.x;done ``` +5. Check NPU TLS Configuration + +```bash +# The tls settings should be consistent across all nodes +for i in {0..7}; do hccn_tool -i $i -tls -g ; done | grep switch +``` + :::: ::::: diff --git a/docs/source/tutorials/pd_disaggregation_mooncake_single_node.md b/docs/source/tutorials/pd_disaggregation_mooncake_single_node.md index 44c266d1..a7a16feb 100644 --- a/docs/source/tutorials/pd_disaggregation_mooncake_single_node.md +++ b/docs/source/tutorials/pd_disaggregation_mooncake_single_node.md @@ -27,7 +27,7 @@ for i in {0..7}; do hccn_tool -i $i -netdetect -g ; done for i in {0..7}; do hccn_tool -i $i -gateway -g ; done ``` -2. Check NPU network configuration: +2. Check NPU HCCN Configuration: Ensure that the hccn.conf file exists in the environment. If using Docker, mount it into the container. @@ -41,6 +41,20 @@ cat /etc/hccn.conf for i in {0..7}; do hccn_tool -i $i -ip -g;done ``` +4. Cross-Node PING Test + +```bash +# Execute on the target node (replace 'x.x.x.x' with actual npu ip address) +for i in {0..7}; do hccn_tool -i $i -ping -g address x.x.x.x;done +``` + +5. Check NPU TLS Configuration + +```bash +# The tls settings should be consistent across all nodes +for i in {0..7}; do hccn_tool -i $i -tls -g ; done | grep switch +``` + ## Run with Docker Start a Docker container. diff --git a/docs/source/user_guide/feature_guide/kv_pool.md b/docs/source/user_guide/feature_guide/kv_pool.md index 4371ce92..01e44ce4 100644 --- a/docs/source/user_guide/feature_guide/kv_pool.md +++ b/docs/source/user_guide/feature_guide/kv_pool.md @@ -24,7 +24,7 @@ export PYTHONHASHSEED=0 ## Example of using Mooncake as a KV Pool backend * Software: - * Check NPU network configuration: + * Check NPU HCCN Configuration: Ensure that the hccn.conf file exists in the environment. If using Docker, mount it into the container.