diff --git a/recipies/gb200-fp4/1k8k/low-latency.yaml b/recipies/gb200-fp4/1k8k/low-latency.yaml
new file mode 100644
index 00000000..933e4a14
--- /dev/null
+++ b/recipies/gb200-fp4/1k8k/low-latency.yaml
@@ -0,0 +1,111 @@
+name: "gb200-fp4-1p2d"
+
+model:
+  path: "dsfp4"
+  container: "lmsysorg/sglang:dev-cu13"
+  precision: "fp4"
+
+resources:
+  gpu_type: "gb200"
+  prefill_nodes: 1
+  decode_nodes: 2
+  prefill_workers: 1
+  decode_workers: 2
+  gpus_per_node: 4
+
+backend:
+
+  prefill_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_DECODE_BOOTSTRAP_TIMEOUT: "1000"
+    #SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    #SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_ENABLE_JIT_DEEPGEMM: "false"
+    SGLANG_ENABLE_FLASHINFER_GEMM: "true" 
+
+  decode_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_DECODE_BOOTSTRAP_TIMEOUT: "1000"
+    # SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    # SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_ENABLE_JIT_DEEPGEMM: "false"
+    SGLANG_ENABLE_FLASHINFER_GEMM: "true" 
+
+  sglang_config:
+    prefill:
+      disaggregation-mode: "prefill"
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      trust-remote-code: true
+      disable-radix-cache: true
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_trtllm"
+      stream-interval: 10
+      watchdog-timeout: 1000000
+      context-length: 9200
+      mem-fraction-static: 0.95
+      max-total-tokens: 8192
+      chunked-prefill-size: 8192
+      disable-cuda-graph: true
+      max-running-requests: 512
+      scheduler-recv-interval: 10
+      moe-dense-tp-size: 1
+      load-balance-method: "round_robin"
+      disaggregation-bootstrap-port: 30001
+      data-parallel-size: 1
+      tensor-parallel-size: 4
+      expert-parallel-size: 1
+
+    decode:
+      disaggregation-mode: "decode"
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      prefill-round-robin-balance: true
+      trust-remote-code: true
+      disable-radix-cache: true
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_trtllm"
+      disaggregation-bootstrap-port: 30001
+      stream-interval: 10
+      watchdog-timeout: 1000000
+      context-length: 9200
+      mem-fraction-static: 0.95
+      chunked-prefill-size: 8192
+      cuda-graph-max-bs: 256
+      scheduler-recv-interval: 10
+      moe-dense-tp-size: 1
+      tensor-parallel-size: 4
+      expert-parallel-size: 1
+
+benchmark:
+  type: "sa-bench"
+  isl: 1024
+  osl: 8192
+  concurrencies: "4x8x32x64x112"
+  req_rate: "inf"
diff --git a/recipies/gb200-fp4/1k8k/max-tpt.yaml b/recipies/gb200-fp4/1k8k/max-tpt.yaml
new file mode 100644
index 00000000..8a8fed77
--- /dev/null
+++ b/recipies/gb200-fp4/1k8k/max-tpt.yaml
@@ -0,0 +1,177 @@
+# 4P1D, with 12 Decode Nodes. Uses single batch overlap
+
+name: "gb200-fp4-max-tpt"
+
+model:
+  path: "dsfp4"
+  container: "lmsysorg/sglang:dev-cu13"
+  precision: "fp4"
+
+resources:
+  gpu_type: "gb200"
+  prefill_nodes: 4
+  decode_nodes: 12
+  prefill_workers: 4
+  decode_workers: 1
+  gpus_per_node: 4
+
+backend:
+
+  # Prefill-specific environment variables
+  prefill_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_HACK_SEQ_BOOTSTRAP_ROOM: "1"
+    MC_TE_METRIC: "true"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+
+  # Decode-specific environment variables
+  decode_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_HACK_SEQ_BOOTSTRAP_ROOM: "1"
+    MC_TE_METRIC: "true"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+    SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: "1024"
+    SGLANG_MOE_NVFP4_DISPATCH: "1"
+    SGLANG_FLASHINFER_FP4_GEMM_BACKEND: "cutlass"
+
+  sglang_config:
+    prefill:
+      # Model configuration
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      trust-remote-code: true
+
+      # KV cache and attention
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+
+      # Quantization
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_cutlass"
+
+      # Radix cache disabled
+      disable-radix-cache: true
+      disable-chunked-prefix-cache: true
+
+      # Other flags
+      stream-interval: 50
+      decode-log-interval: 1000
+      watchdog-timeout: 1000000
+      context-length: 9200
+      disable-shared-experts-fusion: true
+      eplb-algorithm: "deepseek"
+      disaggregation-bootstrap-port: 30001
+
+      # Prefill-specific mode
+      disaggregation-mode: "prefill"
+
+      # Memory and token limits
+      mem-fraction-static: 0.84
+      max-total-tokens: 131072
+      max-prefill-tokens: 32768
+      chunked-prefill-size: 65536
+      enable-single-batch-overlap: true
+
+      # Request handling
+      max-running-requests: 30000
+      load-balance-method: "round_robin"
+
+      # Performance optimizations
+      disable-cuda-graph: true
+      enable-dp-attention: true
+
+      # Parallelism
+      tp-size: 4
+      dp-size: 4
+      ep-size: 4
+
+    decode:
+      # Model configuration
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      trust-remote-code: true
+
+      # KV cache and attention
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+
+      # Quantization
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_cutedsl"
+
+      # Radix cache disabled
+      disable-radix-cache: true
+      disable-chunked-prefix-cache: true
+
+      # Other flags
+      stream-interval: 50
+      decode-log-interval: 1000
+      watchdog-timeout: 1000000
+      context-length: 9200
+      disable-shared-experts-fusion: true
+      eplb-algorithm: "deepseek"
+      disaggregation-bootstrap-port: 30001
+
+      # Decode-specific mode
+      disaggregation-mode: "decode"
+
+      # Memory and token limits
+      mem-fraction-static: 0.83
+      max-total-tokens: 3122380
+      chunked-prefill-size: 786432
+
+      # Request handling
+      max-running-requests: 67584
+      enable-single-batch-overlap: true
+
+      # DeepEP configuration
+      moe-a2a-backend: "deepep"
+      deepep-mode: "low_latency"
+      ep-dispatch-algorithm: "static"
+      ep-num-redundant-experts: 32
+
+      # CUDA graphs (extensive batch size list)
+      cuda-graph-bs: [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 264, 272, 280, 288, 296, 304, 312, 320, 328, 336, 344, 352, 360, 368, 376, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 1024]
+      num-reserved-decode-tokens: 112
+
+      # Additional decode optimizations
+      moe-dense-tp-size: 1
+      enable-dp-lm-head: true
+      prefill-round-robin-balance: true
+      enable-dp-attention: true
+
+      # Parallelism
+      tp-size: 48
+      dp-size: 48
+      ep-size: 48
+
+benchmark:
+  type: "sa-bench"
+  isl: 1024
+  osl: 8192
+  concurrencies: "1x128x512x2048x4096x8192"
+  req_rate: "inf"
diff --git a/recipies/gb200-fp4/1k8k/mid-curve.yaml b/recipies/gb200-fp4/1k8k/mid-curve.yaml
new file mode 100644
index 00000000..c461fa54
--- /dev/null
+++ b/recipies/gb200-fp4/1k8k/mid-curve.yaml
@@ -0,0 +1,177 @@
+# 4P1D, with 8 Decode Nodes. Does not use single batch overlap but allows us to currently drive higher 
+# per gpu throughput
+
+name: "gb200-fp4-max-tpt-2"
+
+model:
+  path: "dsfp4"
+  container: "lmsysorg/sglang:dev-cu13"
+  precision: "fp4"
+
+resources:
+  gpu_type: "gb200"
+  prefill_nodes: 4
+  decode_nodes: 8
+  prefill_workers: 4
+  decode_workers: 1
+  gpus_per_node: 4
+
+backend:
+
+  # Prefill-specific environment variables
+  prefill_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_HACK_SEQ_BOOTSTRAP_ROOM: "1"
+    MC_TE_METRIC: "true"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+
+  # Decode-specific environment variables
+  decode_environment:
+    TORCH_DISTRIBUTED_DEFAULT_TIMEOUT: "1800"
+    PYTHONUNBUFFERED: "1"
+    DYN_SKIP_SGLANG_LOG_FORMATTING: "1"
+    SGLANG_NVFP4_CKPT_FP8_GEMM_IN_ATTN: "1"
+    SGLANG_PER_TOKEN_GROUP_QUANT_8BIT_V2: "1"
+    SGLANG_DISAGGREGATION_HEARTBEAT_MAX_FAILURE: "100000"
+    SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT: "100000"
+    SGLANG_DISAGGREGATION_WAITING_TIMEOUT: "100000"
+    SGLANG_HACK_SEQ_BOOTSTRAP_ROOM: "1"
+    MC_TE_METRIC: "true"
+    MC_FORCE_MNNVL: "1"
+    NCCL_MNNVL_ENABLE: "1"
+    NCCL_CUMEM_ENABLE: "1"
+    SGLANG_MOONCAKE_CUSTOM_MEM_POOL: "True"
+    SGLANG_USE_MESSAGE_QUEUE_BROADCASTER: "0"
+    SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
+    SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: "1024"
+    SGLANG_MOE_NVFP4_DISPATCH: "1"
+    SGLANG_FLASHINFER_FP4_GEMM_BACKEND: "cutlass"
+
+  sglang_config:
+    prefill:
+      # Model configuration
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      trust-remote-code: true
+
+      # KV cache and attention
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+
+      # Quantization
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_cutlass"
+
+      # Radix cache disabled
+      disable-radix-cache: true
+      disable-chunked-prefix-cache: true
+
+      # Other flags
+      stream-interval: 50
+      decode-log-interval: 1000
+      watchdog-timeout: 1000000
+      context-length: 9200
+      disable-shared-experts-fusion: true
+      eplb-algorithm: "deepseek"
+      disaggregation-bootstrap-port: 30001
+
+      # Prefill-specific mode
+      disaggregation-mode: "prefill"
+
+      # Memory and token limits
+      mem-fraction-static: 0.84
+      max-total-tokens: 131072
+      max-prefill-tokens: 32768
+      chunked-prefill-size: 65536
+      enable-single-batch-overlap: true
+
+      # Request handling
+      max-running-requests: 30000
+      load-balance-method: "round_robin"
+
+      # Performance optimizations
+      disable-cuda-graph: true
+      enable-dp-attention: true
+
+      # Parallelism
+      tp-size: 4
+      dp-size: 4
+      ep-size: 4
+
+    decode:
+      # Model configuration
+      served-model-name: "deepseek-ai/DeepSeek-R1"
+      model-path: "/model/"
+      trust-remote-code: true
+
+      # KV cache and attention
+      kv-cache-dtype: "fp8_e4m3"
+      attention-backend: "trtllm_mla"
+
+      # Quantization
+      quantization: "modelopt_fp4"
+      moe-runner-backend: "flashinfer_cutedsl"
+
+      # Radix cache disabled
+      disable-radix-cache: true
+      disable-chunked-prefix-cache: true
+
+      # Other flags
+      stream-interval: 50
+      decode-log-interval: 1000
+      watchdog-timeout: 1000000
+      context-length: 9200
+      disable-shared-experts-fusion: true
+      eplb-algorithm: "deepseek"
+      disaggregation-bootstrap-port: 30001
+
+      # Decode-specific mode
+      disaggregation-mode: "decode"
+
+      # Memory and token limits
+      mem-fraction-static: 0.83
+      max-total-tokens: 3122380
+      chunked-prefill-size: 786432
+
+      # Request handling
+      max-running-requests: 67584
+
+      # DeepEP configuration
+      moe-a2a-backend: "deepep"
+      deepep-mode: "low_latency"
+      ep-dispatch-algorithm: "static"
+      ep-num-redundant-experts: 32
+
+      # CUDA graphs (extensive batch size list)
+      cuda-graph-bs: [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 264, 272, 280, 288, 296, 304, 312, 320, 328, 336, 344, 352, 360, 368, 376, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 1024]
+      num-reserved-decode-tokens: 112
+
+      # Additional decode optimizations
+      moe-dense-tp-size: 1
+      enable-dp-lm-head: true
+      prefill-round-robin-balance: true
+      enable-dp-attention: true
+
+      # Parallelism
+      tp-size: 32
+      dp-size: 32
+      ep-size: 32
+
+benchmark:
+  type: "sa-bench"
+  isl: 1024
+  osl: 8192
+  concurrencies: "1x128x512x2048x4096x8192"
+  req_rate: "inf"