diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p1d-tp8-tp8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p1d-tp8-tp8-mtp.yaml
new file mode 100644
index 0000000000..685537c6a6
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p1d-tp8-tp8-mtp.yaml
@@ -0,0 +1,120 @@
+name: "disagg-b200-8k1k-low-latency-1p1d-tp8-tp8-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
+  precision: "fp4"
+
+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
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: nixl
+
+      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: 16
+      cuda-graph-max-bs: 8
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: nixl
+
+      tensor-parallel-size: 8
+      data-parallel-size: 1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      speculative-algo: "EAGLE"
+      speculative-num-steps: 3
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 4
+
+      mem-fraction-static: 0.9
+      max-running-requests: 8
+      cuda-graph-max-bs: 8
+      swa-full-tokens-ratio: 0.1
+      context-length: 16384
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  random_range_ratio: 0.8
+  concurrencies: "1"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p6d-dep8-tp8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p6d-dep8-tp8-mtp.yaml
new file mode 100644
index 0000000000..18b377b863
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p6d-dep8-tp8-mtp.yaml
@@ -0,0 +1,127 @@
+name: "disagg-b200-8k1k-low-latency-1p6d-dep8-tp8-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
+  precision: "fp4"
+
+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: 6
+  decode_workers: 6
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "9216"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: nixl
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+
+      mem-fraction-static: 0.9
+      max-running-requests: 256
+      cuda-graph-max-bs: 128
+      chunked-prefill-size: 65536
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: nixl
+
+      tensor-parallel-size: 8
+      data-parallel-size: 1
+      expert-parallel-size: 1
+
+      moe-runner-backend: "flashinfer_mxfp4"
+      disable-flashinfer-autotune: true
+
+      speculative-algo: "EAGLE"
+      speculative-num-steps: 3
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 4
+
+      mem-fraction-static: 0.9
+      max-running-requests: 128
+      cuda-graph-max-bs: 128
+      swa-full-tokens-ratio: 0.1
+      context-length: 16384
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  random_range_ratio: 0.8
+  concurrencies: "32x64x128"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p1d-dep8-dep8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p1d-dep8-dep8-mtp.yaml
new file mode 100644
index 0000000000..ea30d07e55
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p1d-dep8-dep8-mtp.yaml
@@ -0,0 +1,128 @@
+name: "disagg-b200-8k1k-mid-curve-1p1d-dep8-dep8-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
+  precision: "fp4"
+
+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
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "9216"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "4096"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "0"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: nixl
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+      mem-fraction-static: 0.8
+      max-running-requests: 1024
+      cuda-graph-max-bs: 1024
+      chunked-prefill-size: 65536
+      stream-interval: 60
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: nixl
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+      speculative-algo: "EAGLE"
+      speculative-num-steps: 3
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 4
+      mem-fraction-static: 0.9
+      max-running-requests: 1536
+      cuda-graph-max-bs: 1024
+      swa-full-tokens-ratio: 0.15
+      context-length: 16384
+      stream-interval: 60
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  random_range_ratio: 0.8
+  concurrencies: "256x1024"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p2d-dep8-dep8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p2d-dep8-dep8-mtp.yaml
new file mode 100644
index 0000000000..9a6254e989
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p2d-dep8-dep8-mtp.yaml
@@ -0,0 +1,139 @@
+name: "disagg-b200-8k1k-mid-curve-1p2d-dep8-dep8-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
+  precision: "fp4"
+
+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
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "9216"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "2048"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "0"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: nixl
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+
+      mem-fraction-static: 0.8
+      max-running-requests: 512
+      cuda-graph-max-bs: 512
+      chunked-prefill-size: 65536
+      stream-interval: 60
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: nixl
+
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+
+      speculative-algo: "EAGLE"
+      speculative-num-steps: 3
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 4
+
+      mem-fraction-static: 0.85
+      max-running-requests: 1024
+      cuda-graph-max-bs: 512
+      swa-full-tokens-ratio: 0.15
+      context-length: 16384
+      stream-interval: 60
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  random_range_ratio: 0.8
+  concurrencies: "256"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-5p3d-dep8-dep8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-5p3d-dep8-dep8-mtp.yaml
new file mode 100644
index 0000000000..e5d9a708a1
--- /dev/null
+++ b/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-5p3d-dep8-dep8-mtp.yaml
@@ -0,0 +1,128 @@
+name: "disagg-b200-8k1k-mid-curve-5p3d-dep8-dep8-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "92f5b3b8d7dd5ab9179d4b1034bd2c1c0803693e"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05"
+  precision: "fp4"
+
+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: 3
+  decode_workers: 3
+  gpus_per_decode: 8
+
+health_check:
+  max_attempts: 240
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_FORCE_MISS: "1"
+    SGLANG_JIT_DEEPGEMM_FAST_WARMUP: "1"
+    SGLANG_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "9216"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    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_DEFAULT_THINKING: "1"
+    SGLANG_DSV4_REASONING_EFFORT: "max"
+    SGLANG_OPT_SWA_SPLIT_LEAF_ON_INSERT: "1"
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "4096"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_FP4_ACTS: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_USE_MXF4_KIND: "1"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    UCX_TLS: "rc,cuda_ipc,cuda_copy,tcp,self"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_OPT_SWA_RELEASE_LEAF_LOCK_AFTER_WINDOW: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "0"
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: nixl
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+      mem-fraction-static: 0.8
+      max-running-requests: 1024
+      cuda-graph-max-bs: 1024
+      chunked-prefill-size: 65536
+      stream-interval: 60
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: nixl
+      tensor-parallel-size: 8
+      data-parallel-size: 8
+      expert-parallel-size: 8
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+      moe-a2a-backend: "megamoe"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+      speculative-algo: "EAGLE"
+      speculative-num-steps: 3
+      speculative-eagle-topk: 1
+      speculative-num-draft-tokens: 4
+      mem-fraction-static: 0.9
+      max-running-requests: 2560
+      cuda-graph-max-bs: 1024
+      swa-full-tokens-ratio: 0.15
+      context-length: 16384
+      stream-interval: 60
+
+benchmark:
+  type: "sa-bench"
+  isl: 8192
+  osl: 1024
+  random_range_ratio: 0.8
+  concurrencies: "6144"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 757a15c0e3..5c049d9f0c 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -5313,6 +5313,93 @@ dsv4-fp4-gb300-dynamo-vllm:
           ep: 16
           dp-attn: true
 
+dsv4-fp4-b200-dynamo-sglang-mtp:
+  image: lmsysorg/sglang:nightly-dev-cu13-20260710-cfc66e05
+  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: nixl
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      - spec-decoding: "mtp"
+        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-low-latency-1p1d-tp8-tp8-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+      - spec-decoding: "mtp"
+        conc-list: [32, 64, 128]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-low-latency-1p6d-dep8-tp8-mtp.yaml"
+        decode:
+          num-worker: 6
+          tp: 8
+          ep: 1
+          dp-attn: false
+      - spec-decoding: "mtp"
+        conc-list: [256, 1024]
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-b200-mid-curve-1p1d-dep8-dep8-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+      - spec-decoding: "mtp"
+        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-mid-curve-1p2d-dep8-dep8-mtp.yaml"
+        decode:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+      - spec-decoding: "mtp"
+        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-mid-curve-5p3d-dep8-dep8-mtp.yaml"
+        decode:
+          num-worker: 3
+          tp: 8
+          ep: 8
+          dp-attn: true
+
 dsv4-fp4-b200-dynamo-vllm-mtp:
   image: vllm/vllm-openai:vllm-x86_64-cu13-0.25.1-7a33ba9
   model: deepseek-ai/DeepSeek-V4-Pro
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index a1875d61b1..676fc73e7f 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5894,3 +5894,11 @@
     - "Cover the measured resident TP2/EP2 and TP4 Pareto ranges through their HBM capacity knees, with required SGLang metrics exports."
     - "Use SGLang v0.5.17 and disable unstable AITER all-reduce fusion for TP2/EP2 EAGLE rank consistency."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2562
+
+- config-keys:
+    - dsv4-fp4-b200-dynamo-sglang-mtp
+  description:
+    - "Add a DeepSeek-V4-Pro FP4 Dynamo-SGLang MTP configuration for B200 with five 8k/1k disaggregated topologies."
+    - "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
diff --git a/runners/launch_b200-nscale-slurm.sh b/runners/launch_b200-nscale-slurm.sh
index b5a448d307..9b9a1e3f96 100755
--- a/runners/launch_b200-nscale-slurm.sh
+++ b/runners/launch_b200-nscale-slurm.sh
@@ -8,8 +8,9 @@
 # them would force every dgxc path to become an override hook and would let a
 # dgxc-only change silently alter nscale runs.
 #
-# Scope: multi-node Dynamo-vLLM DeepSeek-V4-Pro and Kimi K2.6 FP4 runs on
-# the b200-nscale/b200-new runner labels. Anything else exits non-zero.
+# 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
+# labels. Anything else exits non-zero.
 
 SLURM_PARTITION="batch_1"
 SLURM_ACCOUNT="benchmark"
@@ -49,8 +50,9 @@ else
     exit 1
 fi
 
-if [[ $FRAMEWORK != "dynamo-vllm" ]]; then
-    echo "Unsupported framework for b200-nscale: $FRAMEWORK (only dynamo-vllm)" >&2
+if [[ $FRAMEWORK != "dynamo-vllm" ]] &&
+   [[ $MODEL_PREFIX != "dsv4" || $PRECISION != "fp4" || $FRAMEWORK != "dynamo-sglang" || $SPEC_DECODING != "mtp" ]]; then
+    echo "Unsupported framework/configuration for b200-nscale: $MODEL_PREFIX/$PRECISION/$FRAMEWORK/$SPEC_DECODING" >&2
     exit 1
 fi
 
@@ -59,7 +61,14 @@ export SERVED_MODEL_NAME=$MODEL
 echo "Cloning srt-slurm repository..."
 SRT_REPO_DIR="srt-slurm"
 rm -rf "$SRT_REPO_DIR"
-if [[ $MODEL_PREFIX == "dsv4" ]]; then
+if [[ $MODEL_PREFIX == "dsv4" && $FRAMEWORK == "dynamo-sglang" ]]; then
+    git clone --branch main --single-branch https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR" || exit 1
+    cd "$SRT_REPO_DIR" || exit 1
+    # Pin the srt-slurm revision used by these checked-in recipes.
+    git checkout 04e87fcc505d6d851451781a5499ca19a02ec2b4 || exit 1
+    mkdir -p recipes/sglang/deepseek-v4
+    cp -rT "$GITHUB_WORKSPACE/benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4" recipes/sglang/deepseek-v4
+elif [[ $MODEL_PREFIX == "dsv4" ]]; then
     git clone https://github.com/NVIDIA/srt-slurm.git "$SRT_REPO_DIR" || exit 1
     cd "$SRT_REPO_DIR" || exit 1
     git checkout aflowers/vllm-gb200-v0.20.0 || exit 1
@@ -165,6 +174,7 @@ model_paths:
 # Container aliases
 containers:
   dynamo-vllm: "${SQUASH_FILE}"
+  dynamo-sglang: "${SQUASH_FILE}"
   "${IMAGE}": "${SQUASH_FILE}"
   nginx-sqsh: "${NGINX_SQUASH_FILE}"
 use_exclusive_sbatch_directive: true
@@ -201,8 +211,9 @@ sed -i 's/^  max_attempts: [0-9]*/  max_attempts: 720/' "$CONFIG_PATH"
 inject_synthetic_acceptance "$CONFIG_PATH" "$FRAMEWORK" || exit 1
 
 SRTCTL_PREFLIGHT_ARGS=()
-# Kimi K2.6 weights are staged on the Slurm compute nodes, not the login node.
-if [[ $MODEL_PREFIX == "kimik2.6" ]]; then
+# These weights are staged on the Slurm compute nodes, not the login node.
+if [[ $MODEL_PREFIX == "kimik2.6" ]] ||
+   [[ $MODEL_PREFIX == "dsv4" && $FRAMEWORK == "dynamo-sglang" ]]; then
     SRTCTL_PREFLIGHT_ARGS+=(--no-preflight)
 fi