diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-dep8.yaml
new file mode 100644
index 000000000..58c450abb
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-dep8.yaml
@@ -0,0 +1,158 @@
+name: "disagg-b200-1p1d-dep8-dep8-c512"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 1
+  decode_workers: 1
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "256x512"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-tp8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-tp8.yaml
new file mode 100644
index 000000000..ea5b1a17f
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-tp8.yaml
@@ -0,0 +1,145 @@
+name: "disagg-b200-1p1d-dep8-tp8-4-c64"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 1
+  decode_workers: 1
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_USE_JIT_NORM: "1"
+    SGLANG_OPT_USE_JIT_INDEXER_METADATA: "1"
+    SGLANG_OPT_USE_TOPK_V2: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      disable-radix-cache: true
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 8
+      data-parallel-size:   1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      mem-fraction-static: 0.9
+      max-running-requests: 1024
+      cuda-graph-max-bs:    512
+      swa-full-tokens-ratio: 0.1
+      context-length: 16384
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "32x64"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-tp8-tp8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-tp8-tp8.yaml
new file mode 100644
index 000000000..cdef4e344
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-tp8-tp8.yaml
@@ -0,0 +1,120 @@
+name: "disagg-b200-1p1d-tp8-tp8-c1"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 1
+  decode_workers: 1
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      disable-radix-cache: true
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 8
+      data-parallel-size:   1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      mem-fraction-static: 0.90
+      max-running-requests: 1024
+      cuda-graph-max-bs: 512
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      disable-radix-cache: true
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 8
+      data-parallel-size:   1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      mem-fraction-static: 0.9
+      max-running-requests: 1024
+      cuda-graph-max-bs:    512
+      swa-full-tokens-ratio: 0.1
+      context-length: 16384
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "1"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p2d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p2d-dep8-dep8.yaml
new file mode 100644
index 000000000..fa7206ea2
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p2d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-1p2d-dep8-dep8-c256"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 2
+  decode_workers: 2
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "256"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-dep8.yaml
new file mode 100644
index 000000000..115d4419f
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-1p4d-dep8-dep8-c256"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 4
+  decode_workers: 4
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "256"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-tp8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-tp8.yaml
new file mode 100644
index 000000000..a8408962d
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-tp8.yaml
@@ -0,0 +1,145 @@
+name: "disagg-b200-1p4d-dep8-tp8-c64"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 1
+  prefill_workers: 1
+  gpus_per_prefill: 8
+  decode_nodes: 4
+  decode_workers: 4
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_USE_JIT_NORM: "1"
+    SGLANG_OPT_USE_JIT_INDEXER_METADATA: "1"
+    SGLANG_OPT_USE_TOPK_V2: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      disable-radix-cache: true
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 8
+      data-parallel-size:   1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      mem-fraction-static: 0.9
+      max-running-requests: 1024
+      cuda-graph-max-bs:    512
+      swa-full-tokens-ratio: 0.1
+      context-length: 16384
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "64"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-3p2d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-3p2d-dep8-dep8.yaml
new file mode 100644
index 000000000..cd1592641
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-3p2d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-3p2d-dep8-dep8-c2048"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 3
+  prefill_workers: 3
+  gpus_per_prefill: 8
+  decode_nodes: 2
+  decode_workers: 2
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "2048"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-4p2d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-4p2d-dep8-dep8.yaml
new file mode 100644
index 000000000..9fb1a075e
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-4p2d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-4p2d-dep8-dep8-c4096"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 4
+  prefill_workers: 4
+  gpus_per_prefill: 8
+  decode_nodes: 2
+  decode_workers: 2
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "4096"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-5p2d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-5p2d-dep8-dep8.yaml
new file mode 100644
index 000000000..098a038ba
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-5p2d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-5p2d-dep8-dep8-c6144"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 5
+  prefill_workers: 5
+  gpus_per_prefill: 8
+  decode_nodes: 2
+  decode_workers: 2
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "6144"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-6p2d-dep8-dep8.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-6p2d-dep8-dep8.yaml
new file mode 100644
index 000000000..a635b781e
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-6p2d-dep8-dep8.yaml
@@ -0,0 +1,159 @@
+name: "disagg-b200-6p2d-dep8-dep8-c8192"
+
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  precision: "fp4"
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "b200"
+  gpus_per_node: 8
+  prefill_nodes: 6
+  prefill_workers: 6
+  gpus_per_prefill: 8
+  decode_nodes: 2
+  decode_workers: 2
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: false
+  env:
+    DYN_ROUTER_LOAD_BLOCK_SIZE: "1"
+  args:
+    router-mode: "kv"
+    router-kv-overlap-score-weight: 0
+    router-queue-threshold: 64
+    router-temperature: 0.5
+    no-kv-events: true
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "8192"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    SGLANG_OPT_FP8_WO_A_GEMM: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_ENABLE_THINKING: "1"
+    SGLANG_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "1280"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_OPT_USE_ONLINE_COMPRESS: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_CLIP_MAX_NEW_TOKENS_ESTIMATION: "8"
+    MC_FORCE_MNNVL: "1"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_LOG_FORWARD_ITERS: "1"
+    SGLANG_LOG_MS: "1"
+    SGLANG_REQUEST_STATE_WAIT_TIMEOUT: "60"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":88,"num_max_nvl_chunked_send_tokens":28,"num_max_nvl_chunked_recv_tokens":512},"normal_combine": {"num_sms":88,"num_max_nvl_chunked_send_tokens":16,"num_max_nvl_chunked_recv_tokens":512}}'
+      moe-dense-tp-size: 1
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      mem-fraction-static: 0.80
+      max-running-requests: 1024
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      trust-remote-code: true
+      watchdog-timeout: 86400
+      skip-tokenizer-init: true
+      stream-interval: 60
+
+      load-balance-method: "total_requests"
+      moe-a2a-backend: "megamoe"
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+      disaggregation-decode-polling-interval: 8
+
+      mem-fraction-static: 0.94
+      swa-full-tokens-ratio: 0.056
+      context-length: 9216
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      max-running-requests: 21504
+      cuda-graph-max-bs: 1280
+
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  concurrencies: "8192"
+  req_rate: "inf"
+  use_chat_template: false
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 5c049d9f0..b3cbe534a 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -4738,6 +4738,164 @@ dsv4-fp4-gb200-dynamo-vllm-mtp2-nosynthetic:
           ep: 8
           dp-attn: true
 
+# DSV4 B200 disaggregated Dynamo SGLang STP configuration.
+dsv4-fp4-b200-dynamo-sglang:
+  image: lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: b200-nscale
+  precision: fp4
+  framework: dynamo-sglang
+  router: { name: dynamo-router, version: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e" }
+  kv-p2p-transfer: mooncake
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # 1p1d-tp8-tp8 (pure TP). 2 nodes (1+1).
+      - conc-list: [1]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-tp8-tp8.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+      # 1p1d-dep8-tp8: DEP8 prefill + TP8 decode. 2 nodes (1+1).
+      - conc-list: [32, 64]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-tp8.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+      # 1p1d-dep8-dep8: DEP8 prefill + DEP8 decode. 2 nodes (1+1).
+      - conc-list: [256, 512]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p1d-dep8-dep8.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 1p4d-dep8-tp8: DEP8 prefill + 4x TP8 decode. 5 nodes (1+4).
+      - conc-list: [64]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-tp8.yaml"
+        decode:
+          num-worker: 4
+          tp: 8
+          ep: 1
+          dp-attn: false
+      # 1p2d-dep8-dep8: DEP8 prefill + 2x DEP8 decode. 3 nodes (1+2).
+      - conc-list: [256]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p2d-dep8-dep8.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 1p4d-dep8-dep8: DEP8 prefill + 4x DEP8 decode. 5 nodes (1+4).
+      - conc-list: [256]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-1p4d-dep8-dep8.yaml"
+        decode:
+          num-worker: 4
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 3p2d-dep8-dep8: 3x DEP8 prefill + 2x DEP8 decode. 5 nodes (3+2).
+      - conc-list: [2048]
+        prefill:
+          num-worker: 3
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-3p2d-dep8-dep8.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 4p2d-dep8-dep8: 4x DEP8 prefill + 2x DEP8 decode. 6 nodes (4+2).
+      - conc-list: [4096]
+        prefill:
+          num-worker: 4
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-4p2d-dep8-dep8.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 5p2d-dep8-dep8: 5x DEP8 prefill + 2x DEP8 decode. 7 nodes (5+2).
+      - conc-list: [6144]
+        prefill:
+          num-worker: 5
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-5p2d-dep8-dep8.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # 6p2d-dep8-dep8: 6x DEP8 prefill + 2x DEP8 decode. 8 nodes (6+2).
+      - conc-list: [8192]
+        prefill:
+          num-worker: 6
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-6p2d-dep8-dep8.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+
 dsv4-fp4-gb200-dynamo-sglang:
   image: lmsysorg/sglang:nightly-dev-cu13-20260528-0abe6a85
   model: deepseek-ai/DeepSeek-V4-Pro
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 676fc73e7..7ede11262 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5902,3 +5902,11 @@
     - "Use NIXL for KV transfer with EAGLE speculative decoding and chat-formatted benchmark inputs."
     - "Image: lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2554
+
+- config-keys:
+    - dsv4-fp4-b200-dynamo-sglang
+  description:
+    - "Add a DeepSeek-V4-Pro FP4 Dynamo-SGLang STP configuration for B200 with ten 8k/1k disaggregated topologies."
+    - "Use Mooncake for KV transfer with raw synthetic benchmark inputs."
+    - "Image: lmsysorg/sglang:nightly-dev-cu13-20260708-b3632494"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2560
diff --git a/runners/launch_b200-nscale-slurm.sh b/runners/launch_b200-nscale-slurm.sh
index 9b9a1e3f9..826a44b44 100755
--- a/runners/launch_b200-nscale-slurm.sh
+++ b/runners/launch_b200-nscale-slurm.sh
@@ -9,7 +9,8 @@
 # dgxc-only change silently alter nscale runs.
 #
 # Scope: multi-node Dynamo-vLLM DeepSeek-V4-Pro and Kimi K2.6 FP4 runs, plus
-# DeepSeek-V4-Pro FP4 Dynamo-SGLang MTP, on the b200-nscale/b200-new runner
+# DeepSeek-V4-Pro FP4 Dynamo-SGLang STP and MTP runs, on the
+# b200-nscale/b200-new runner
 # labels. Anything else exits non-zero.
 
 SLURM_PARTITION="batch_1"
@@ -51,7 +52,8 @@ else
 fi
 
 if [[ $FRAMEWORK != "dynamo-vllm" ]] &&
-   [[ $MODEL_PREFIX != "dsv4" || $PRECISION != "fp4" || $FRAMEWORK != "dynamo-sglang" || $SPEC_DECODING != "mtp" ]]; then
+   [[ $MODEL_PREFIX != "dsv4" || $PRECISION != "fp4" || $FRAMEWORK != "dynamo-sglang" ||
+      ( $SPEC_DECODING != "none" && $SPEC_DECODING != "mtp" ) ]]; then
     echo "Unsupported framework/configuration for b200-nscale: $MODEL_PREFIX/$PRECISION/$FRAMEWORK/$SPEC_DECODING" >&2
     exit 1
 fi