-
Notifications
You must be signed in to change notification settings - Fork 253
Add DeepSeek-V4-Pro FP4 B200 Dynamo TensorRT-LLM recipes / 添加 DeepSeek-V4-Pro FP4 B200 Dynamo TensorRT-LLM 配置 #2552
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
RohitNagraj
wants to merge
2
commits into
main
Choose a base branch
from
dsv4-fp4-b200-dynamo-trt
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
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
65 changes: 65 additions & 0 deletions
65
benchmarks/multi_node/srt-slurm-recipes/configs/moe_load_balancer_ctx_ep4_384.yaml
Large diffs are not rendered by default.
Oops, something went wrong.
65 changes: 65 additions & 0 deletions
65
benchmarks/multi_node/srt-slurm-recipes/configs/moe_load_balancer_gen_ep8_slots384.yaml
Large diffs are not rendered by default.
Oops, something went wrong.
123 changes: 123 additions & 0 deletions
123
...recipes/trtllm/deepseek-v4/8k1k/b200/disagg-b200-8k1k-1p2d-dep8-dep8-b4-eplb384-mtp3.yaml
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 +1,123 @@ | ||
| name: disagg-b200-8k1k-1p2d-dep8-dep8-b4-eplb384-mtp3 | ||
| model: | ||
| path: deepseek-v4-pro | ||
| container: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc23 | ||
| precision: fp4 | ||
| dynamo: | ||
| install: true | ||
| wheel: "1.4.0.dev20260730" | ||
| request_plane: tcp | ||
| resources: | ||
| gpu_type: b200 | ||
| prefill_nodes: 1 | ||
| prefill_workers: 1 | ||
| gpus_per_prefill: 8 | ||
| decode_nodes: 2 | ||
| decode_workers: 2 | ||
| gpus_per_decode: 8 | ||
| gpus_per_node: 8 | ||
| backend: | ||
| type: trtllm | ||
| prefill_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS: '1.82' | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| decode_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS: '1.82' | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| trtllm_config: | ||
| prefill: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| disable_overlap_scheduler: true | ||
| enable_attention_dp: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.5 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 2 | ||
| max_num_tokens: 8192 | ||
| max_seq_len: 8232 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_ctx_ep4_384.yaml | ||
| moe_expert_parallel_size: 8 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 3 | ||
| tensor_parallel_size: 8 | ||
| decode: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| batch_sizes: | ||
| - 1 | ||
| - 2 | ||
| - 4 | ||
| enable_padding: true | ||
| enable_attention_dp: true | ||
| enable_lm_head_tp_in_adp: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.8 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 4 | ||
| max_num_tokens: 16 | ||
| max_seq_len: 9256 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_gen_ep8_slots384.yaml | ||
| use_low_precision_moe_combine: true | ||
| moe_expert_parallel_size: 8 | ||
| num_postprocess_workers: 4 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 3 | ||
| stream_interval: 100 | ||
| tensor_parallel_size: 8 | ||
| benchmark: | ||
| type: sa-bench | ||
| isl: 8192 | ||
| osl: 1024 | ||
| concurrencies: "64" | ||
| req_rate: inf | ||
| random_range_ratio: 0.8 | ||
| use_chat_template: true | ||
| custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer" | ||
| frontend: | ||
| type: dynamo | ||
| enable_multiple_frontends: false | ||
| health_check: | ||
| max_attempts: 540 | ||
| interval_seconds: 10 | ||
| environment: | ||
| TRTLLM_SERVER_DISABLE_GC: '1' |
116 changes: 116 additions & 0 deletions
116
...recipes/trtllm/deepseek-v4/8k1k/b200/disagg-b200-8k1k-1p3d-dep8-dep8-b8-eplb384-mtp0.yaml
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 +1,116 @@ | ||
| name: disagg-b200-8k1k-1p3d-dep8-dep8-b8-eplb384-mtp0 | ||
| model: | ||
| path: deepseek-v4-pro | ||
| container: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc23 | ||
| precision: fp4 | ||
| dynamo: | ||
| install: true | ||
| wheel: "1.4.0.dev20260730" | ||
| request_plane: tcp | ||
| resources: | ||
| gpu_type: b200 | ||
| prefill_nodes: 1 | ||
| prefill_workers: 1 | ||
| gpus_per_prefill: 8 | ||
| decode_nodes: 3 | ||
| decode_workers: 3 | ||
| gpus_per_decode: 8 | ||
| gpus_per_node: 8 | ||
| backend: | ||
| type: trtllm | ||
| prefill_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| decode_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| trtllm_config: | ||
| prefill: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| disable_overlap_scheduler: true | ||
| enable_attention_dp: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.5 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 2 | ||
| max_num_tokens: 8192 | ||
| max_seq_len: 8232 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_ctx_ep4_384.yaml | ||
| moe_expert_parallel_size: 8 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| tensor_parallel_size: 8 | ||
| decode: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| batch_sizes: | ||
| - 1 | ||
| - 2 | ||
| - 4 | ||
| - 8 | ||
| enable_padding: true | ||
| enable_attention_dp: true | ||
| enable_lm_head_tp_in_adp: false | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.8 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 8 | ||
| max_num_tokens: 8 | ||
| max_seq_len: 9256 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_gen_ep8_slots384.yaml | ||
| use_low_precision_moe_combine: true | ||
| moe_expert_parallel_size: 8 | ||
| num_postprocess_workers: 4 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| stream_interval: 100 | ||
| tensor_parallel_size: 8 | ||
| benchmark: | ||
| type: sa-bench | ||
| isl: 8192 | ||
| osl: 1024 | ||
| concurrencies: "192" | ||
| req_rate: inf | ||
| random_range_ratio: 0.8 | ||
| use_chat_template: true | ||
| custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer" | ||
| frontend: | ||
| type: dynamo | ||
| enable_multiple_frontends: false | ||
| health_check: | ||
| max_attempts: 540 | ||
| interval_seconds: 10 | ||
| environment: | ||
| TRTLLM_SERVER_DISABLE_GC: '1' |
123 changes: 123 additions & 0 deletions
123
...recipes/trtllm/deepseek-v4/8k1k/b200/disagg-b200-8k1k-1p4d-dep8-dep8-b2-eplb384-mtp3.yaml
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 +1,123 @@ | ||
| name: disagg-b200-8k1k-1p4d-dep8-dep8-b2-eplb384-mtp3 | ||
| model: | ||
| path: deepseek-v4-pro | ||
| container: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc23 | ||
| precision: fp4 | ||
| dynamo: | ||
| install: true | ||
| wheel: "1.4.0.dev20260730" | ||
| request_plane: tcp | ||
| resources: | ||
| gpu_type: b200 | ||
| prefill_nodes: 1 | ||
| prefill_workers: 1 | ||
| gpus_per_prefill: 8 | ||
| decode_nodes: 4 | ||
| decode_workers: 4 | ||
| gpus_per_decode: 8 | ||
| gpus_per_node: 8 | ||
| backend: | ||
| type: trtllm | ||
| prefill_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS: '1.82' | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| decode_environment: | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
| TRTLLM_WORKER_DISABLE_GC: '1' | ||
| TRTLLM_ENABLE_PDL: '1' | ||
| ENROOT_ALLOW_DEV: 'yes' | ||
| NCCL_GRAPH_MIXING_SUPPORT: '0' | ||
| MIMALLOC_PURGE_DELAY: '0' | ||
| TLLM_PROFILE_LOG_RANKS: all | ||
| TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS: '1.82' | ||
| UCX_TLS: rc,cuda_ipc,cuda_copy,sm,self,tcp | ||
| NIXL_PLUGIN_DIR: /opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/plugins | ||
| trtllm_config: | ||
| prefill: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| disable_overlap_scheduler: true | ||
| enable_attention_dp: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.5 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 2 | ||
| max_num_tokens: 8192 | ||
| max_seq_len: 8232 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_ctx_ep4_384.yaml | ||
| moe_expert_parallel_size: 8 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 3 | ||
| tensor_parallel_size: 8 | ||
| decode: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| kv_transfer_timeout_ms: 600000 | ||
| transceiver_runtime: PYTHON | ||
| cuda_graph_config: | ||
| batch_sizes: | ||
| - 1 | ||
| - 2 | ||
| - 4 | ||
| enable_padding: true | ||
| enable_attention_dp: true | ||
| enable_lm_head_tp_in_adp: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| free_gpu_memory_fraction: 0.8 | ||
| tokens_per_block: 128 | ||
| max_batch_size: 2 | ||
| max_num_tokens: 8 | ||
| max_seq_len: 9256 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| load_balancer: /configs/moe_load_balancer_gen_ep8_slots384.yaml | ||
| use_low_precision_moe_combine: true | ||
| moe_expert_parallel_size: 8 | ||
| num_postprocess_workers: 4 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 3 | ||
| stream_interval: 100 | ||
| tensor_parallel_size: 8 | ||
| benchmark: | ||
| type: sa-bench | ||
| isl: 8192 | ||
| osl: 1024 | ||
| concurrencies: "64" | ||
| req_rate: inf | ||
| random_range_ratio: 0.8 | ||
| use_chat_template: true | ||
| custom_tokenizer: "sa_bench_tokenizers.sglang_deepseek_v4.SGLangDeepseekV4Tokenizer" | ||
| frontend: | ||
| type: dynamo | ||
| enable_multiple_frontends: false | ||
| health_check: | ||
| max_attempts: 540 | ||
| interval_seconds: 10 | ||
| environment: | ||
| TRTLLM_SERVER_DISABLE_GC: '1' | ||
Oops, something went wrong.
Oops, something went wrong.
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.
🟡 In
disagg-b200-8k1k-1p4d-dep8-dep8-b2-eplb384-mtp3.yaml, decode'scuda_graph_config.batch_sizesis[1, 2, 4]butdecode.max_batch_sizeis2, so the batch-4 CUDA graph can never be exercised. This looks like a copy-paste leftover from the sibling b4 recipe (disagg-b200-8k1k-1p2d-dep8-dep8-b4-eplb384-mtp3.yaml, which correctly uses[1, 2, 4]withmax_batch_size: 4) —batch_sizesshould be trimmed to[1, 2]here.Extended reasoning...
The bug: In
benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/8k1k/b200/disagg-b200-8k1k-1p4d-dep8-dep8-b2-eplb384-mtp3.yaml, the decode block sets:TensorRT-LLM's decode-side batching can never dispatch more than
max_batch_size(2) requests at once, so the batch-size-4 CUDA graph entry is unreachable — no request stream can ever fill it. This is purely a config-consistency issue, not a crash: TRT-LLM either ignores/clamps cuda-graph batch sizes abovemax_batch_sizeor wastes one extra graph capture (time + a bit of GPU memory) for a size it will never use.Why this happened: Every other recipe added in this PR keeps the largest
cuda_graph_config.batch_sizesentry exactly equal tomax_batch_size— e.g. the siblingdisagg-b200-8k1k-1p2d-dep8-dep8-b4-eplb384-mtp3.yaml(same dep8-dep8/eplb384/mtp3 template, just b4 instead of b2) uses the identical list[1, 2, 4]but withmax_batch_size: 4. Themax_num_tokens: 8in the b2 file (2 requests × 4 tokens/step under MTP draft_len=3) further corroborates that this file was derived from the b4 template by reducingmax_batch_size/max_num_tokensfrom 4→2, but thebatch_sizeslist was never trimmed to match.Step-by-step proof:
max_batch_size: 2— it will never admit a 3rd or 4th concurrent request.batch_sizes: sizes 1, 2, and 4.max(batch_sizes) == max_batch_size; this b2 file is the sole outlier.Fix: Change
batch_sizesto[1, 2]to matchmax_batch_size: 2, consistent with every other recipe in this PR.Why nit, not normal: This doesn't break the run — TensorRT-LLM handles cuda-graph batch sizes above the scheduler cap gracefully (filtering/clamping), so the worst-case impact is a modest amount of wasted graph-capture time and GPU memory at startup, not a functional failure or incorrect output. It's a legitimate cleanup that all three independent verifiers agreed should be fixed but flagged as non-blocking.