This repository was archived by the owner on Apr 20, 2026. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 37
Draft: FP4 Disagg + MTP Configs #48
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,8 @@ | ||
| #!/bin/bash | ||
| BRANCH="dev/mtp_support_for_eagle_worker_v1" | ||
|
|
||
| cd /sgl-workspace/sglang | ||
| git remote add trevor https://github.com/trevor-m/sglang.git | ||
| git fetch trevor $BRANCH | ||
| git checkout "trevor/${BRANCH}" | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,121 @@ | ||
| name: "gb200-fp4-1p2d-mtp" | ||
|
|
||
| model: | ||
| path: "dsfp4" | ||
| container: "0.5.5.post2" | ||
| 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" #instead of SGLANG_FLASHINFER_FP4_GEMM_BACKEND | ||
|
|
||
| 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" #instead of SGLANG_FLASHINFER_FP4_GEMM_BACKEND | ||
|
|
||
| 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: 2200 | ||
| mem-fraction-static: 0.95 | ||
| max-total-tokens: 8192 | ||
| chunked-prefill-size: 8192 | ||
| cuda-graph-max-bs: 256 | ||
| max-running-requests: 512 | ||
| scheduler-recv-interval: 10 | ||
| enable-symm-mem: true | ||
| 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 | ||
| speculative-algorithm: "EAGLE" | ||
| speculative-num-steps: 2 | ||
| speculative-eagle-topk: 1 | ||
| speculative-num-draft-tokens: 3 | ||
|
|
||
| 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: 2200 | ||
| mem-fraction-static: 0.90 | ||
| chunked-prefill-size: 8192 | ||
| cuda-graph-max-bs: 256 | ||
| scheduler-recv-interval: 10 | ||
| enable-symm-mem: true | ||
| moe-dense-tp-size: 1 | ||
| tensor-parallel-size: 4 | ||
| expert-parallel-size: 1 | ||
| speculative-algorithm: "EAGLE" | ||
| speculative-num-steps: 2 | ||
| speculative-eagle-topk: 1 | ||
| speculative-num-draft-tokens: 3 | ||
|
|
||
| benchmark: | ||
| type: "sa-bench" | ||
| isl: 1024 | ||
| osl: 1024 | ||
| concurrencies: "4x8x32x64x112x128x256" | ||
| req_rate: "inf" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,192 @@ | ||
| # 4P1D, with 8 Decode Nodes. Better per-gpu throughput with worse latency. | ||
|
|
||
| name: "gb200-fp4-max-tpt-2-mtp" | ||
|
|
||
| model: | ||
| path: "dsfp4" | ||
| container: "0.5.5.post2" | ||
| 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_CUTEDSL_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: 2176 | ||
| 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 | ||
|
|
||
| # MTP | ||
| speculative-algorithm: "EAGLE" | ||
| speculative-num-steps: 1 | ||
| speculative-eagle-topk: 1 | ||
| speculative-num-draft-tokens: 2 | ||
| speculative-moe-runner-backend: "cutlass" | ||
| speculative-moe-a2a-backend: "none" | ||
|
|
||
| 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: 2176 | ||
| 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: 0.73 | ||
| max-total-tokens: 3122380 | ||
| chunked-prefill-size: 786432 | ||
|
|
||
| # Request handling | ||
| max-running-requests: 33792 #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: 224 #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 | ||
|
|
||
| # MTP | ||
| speculative-algorithm: "EAGLE" | ||
| speculative-num-steps: 1 | ||
| speculative-eagle-topk: 1 | ||
| speculative-num-draft-tokens: 2 | ||
| speculative-moe-runner-backend: "cutlass" | ||
| speculative-moe-a2a-backend: "none" | ||
|
|
||
| benchmark: | ||
| type: "sa-bench" | ||
| isl: 1024 | ||
| osl: 1024 | ||
| concurrencies: "1x128x512x2048x4096x8192x12000x15000" | ||
| req_rate: "inf" |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can we rename this file to
gb200-fp4-mtp-setup.shi dont have a good way of organizing these lol so descriptive naming is probably the best
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What about
checkout-pr-13115.sh?I also found out we need to disable the engine patch since this PR is based on main. I tried rebasing to 0.5.5 but it might have some dependencies on other PRs.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I see. I can assist with this tomorrow