Add DSV4 FP4 GB300 dynamo-sglang MTP disagg benchmarks

.github/configs/nvidia-master.yaml

@@ -8313,3 +8313,110 @@ dsv4-fp4-gb300-dynamo-sglang:
           tp: 12
           ep: 12
           dp-attn: true
+
+# MTP variant of dsv4-fp4-gb300-dynamo-sglang.
+dsv4-fp4-gb300-dynamo-sglang-mtp:
+  image: lmsysorg/sglang:nightly-dev-cu13-20260508-2cf1a4ab
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: gb300-cw
+  precision: fp4
+  framework: dynamo-sglang
+  multinode: true
+  disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # Low-latency baseline: 1p1d-tp4-tp4. 2 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [1]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 1
+          dp-attn: false
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-low-latency-1p1d-tp4-tp4-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # Low-latency 1p6d-dep4-tp4: 1P (DEP=4) + 6 TP=4 decode workers. 7 nodes.
+      # Recipe runs concurrencies=8x32x64; matrix tracks the max.
+      - spec-decoding: "mtp"
+        conc-list: [64]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-low-latency-1p6d-dep4-tp4-mtp.yaml"
+        decode:
+          num-worker: 6
+          tp: 4
+          ep: 1
+          dp-attn: false
+      # Mid curve 1p1d-dep4-dep8. 3 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [256]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-mid-curve-1p1d-dep4-dep8-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # Mid curve 1p1d-dep4-dep16. 5 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [256]
+        prefill:
+          num-worker: 1
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-mid-curve-1p1d-dep4-dep16-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 16
+          ep: 16
+          dp-attn: true
+      # Mid curve 2p1d-dep4-dep8. 4 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [512]
+        prefill:
+          num-worker: 2
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-mid-curve-2p1d-dep4-dep8-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+      # Mid curve 4p1d-dep4-dep8. 6 nodes.
+      - spec-decoding: "mtp"
+        conc-list: [1024]
+        prefill:
+          num-worker: 4
+          tp: 4
+          ep: 4
+          dp-attn: true
+          additional-settings:
+          - "CONFIG_FILE=recipes/sglang/deepseek-v4/8k1k/disagg-mid-curve-4p1d-dep4-dep8-mtp.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-low-latency-1p1d-tp4-tp4-mtp.yaml

@@ -0,0 +1,127 @@
+name: "dsv4-pro-gb300-disagg-8k1k-low-latency-1p1d-tp4-tp4-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "81d0555ee23519cea80a42b4fe824e30368b7300"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260508-2cf1a4ab"
+  precision: "mxfp4"
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "gb300"
+  gpus_per_node: 4
+  prefill_nodes: 1
+  prefill_workers: 1
+  decode_nodes: 1
+  decode_workers: 1
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_DISABLE_REUSE: "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_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"
+
+  decode_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_DISABLE_REUSE: "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_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_OPT_USE_CUSTOM_ALL_REDUCE_V2 intentionally NOT set: CAR_V2
+    # is single-node only and corrupts results in 2-node decode setups.
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4  # gates the dsv4 chat-encoding spec.
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 4
+      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: 8
+      cuda-graph-max-bs: 8
+      chunked-prefill-size: 32768
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4  # gates the dsv4 chat-encoding spec.
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 4
+      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"

benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/8k1k/disagg-low-latency-1p6d-dep4-tp4-mtp.yaml

@@ -0,0 +1,141 @@
+name: "dsv4-pro-gb300-disagg-8k1k-low-latency-1p6d-dep4-tp4-mtp"
+
+frontend:
+  type: dynamo
+  enable_multiple_frontends: true
+  num_additional_frontends: 8
+
+dynamo:
+  hash: "81d0555ee23519cea80a42b4fe824e30368b7300"
+  install: true
+
+model:
+  path: "deepseek-v4-pro"
+  container: "lmsysorg/sglang:nightly-dev-cu13-20260508-2cf1a4ab"
+  precision: "mxfp4"
+
+sbatch_directives:
+  cpus-per-task: "144"
+  mem: "0"
+
+resources:
+  gpu_type: "gb300"
+  gpus_per_node: 4
+  prefill_nodes: 1
+  prefill_workers: 1
+  decode_nodes: 6
+  decode_workers: 6
+
+backend:
+  type: sglang
+
+  prefill_environment:
+    PYTHONUNBUFFERED: "1"
+    SGLANG_RADIX_DISABLE_REUSE: "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_USE_JIT_NORM: "1"
+    SGLANG_OPT_USE_JIT_INDEXER_METADATA: "1"
+    SGLANG_OPT_USE_TOPK_V2: "1"
+
+    SGLANG_OPT_SWA_EVICT_DROP_PAGE_MARGIN: "1"
+    SGLANG_OPT_USE_CUSTOM_ALL_REDUCE_V2: "1"
+    SGLANG_OPT_USE_FAST_MASK_EP: "1"
+    SGLANG_OPT_USE_DEEPGEMM_MEGA_MOE: "1"
+    SGLANG_OPT_FIX_HASH_MEGA_MOE: "1"
+    SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK: "9216"
+    SGLANG_OPT_FIX_MEGA_MOE_MEMORY: "1"
+    SGLANG_OPT_FIX_NEXTN_MEGA_MOE: "1"
+    SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: "0"
+
+    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_DISABLE_REUSE: "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_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_OPT_USE_CUSTOM_ALL_REDUCE_V2 intentionally NOT set: CAR_V2
+    # is single-node only and corrupts results in 2-node decode setups.
+
+  sglang_config:
+    prefill:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4  # gates the dsv4 chat-encoding spec.
+
+      disaggregation-mode: "prefill"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 4
+      data-parallel-size: 4
+      expert-parallel-size: 4
+
+      enable-dp-attention: true
+      enable-dp-lm-head: true
+
+      moe-a2a-backend: "deepep"
+      deepep-config: '{"normal_dispatch":{"num_sms":96},"normal_combine":{"num_sms":96}}'
+
+      mem-fraction-static: 0.9
+      max-running-requests: 128
+      cuda-graph-max-bs: 128
+      chunked-prefill-size: 32768
+
+    decode:
+      served-model-name: "deepseek-ai/DeepSeek-V4-Pro"
+      model-path: "/model/"
+      trust-remote-code: true
+      tool-call-parser: deepseekv4  # gates the dsv4 chat-encoding spec.
+
+      disaggregation-mode: "decode"
+      disaggregation-transfer-backend: mooncake
+
+      tensor-parallel-size: 4
+      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: "8x32x64"
+  req_rate: "inf"
+  use_chat_template: true
+  custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer"