feat(config): add GLM-5.2 GB300 AgentX concurrency-1 disaggregated point / 添加 GLM-5.2 GB300 AgentX 并发度 1 分离式配置 #2720
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 +1,177 @@ | ||
| name: dynamo-disagg-gb300-1p1d-tp8-c1-b1-mtp5 | ||
|
|
||
| model: | ||
| path: nvidia/GLM-5.2-NVFP4 | ||
| container: nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc22.post1 | ||
| precision: fp4 | ||
|
|
||
| dynamo: | ||
| install: true | ||
| wheel: 1.4.0.dev20260807 | ||
| request_plane: tcp | ||
|
|
||
| health_check: | ||
| max_attempts: 270 | ||
| interval_seconds: 10 | ||
|
|
||
| resources: | ||
| gpu_type: gb300 | ||
| gpus_per_node: 4 | ||
| prefill_nodes: 1 | ||
| prefill_workers: 1 | ||
| gpus_per_prefill: 4 | ||
| decode_nodes: 2 | ||
| decode_workers: 1 | ||
| gpus_per_decode: 8 | ||
|
|
||
| backend: | ||
| type: trtllm | ||
| prefill_environment: &server_environment | ||
| HF_HUB_OFFLINE: "1" | ||
| TRANSFORMERS_OFFLINE: "1" | ||
| TQDM_DISABLE: "1" | ||
| HF_HUB_DISABLE_PROGRESS_BARS: "1" | ||
| TLLM_LOG_LEVEL: INFO | ||
| TRTLLM_SERVER_DISABLE_GC: "1" | ||
| TRTLLM_WORKER_DISABLE_GC: "1" | ||
| TRTLLM_ENABLE_PDL: "1" | ||
| NCCL_GRAPH_MIXING_SUPPORT: "0" | ||
| MIMALLOC_PURGE_DELAY: "0" | ||
| PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True | ||
| TRTLLM_SERVE_ENABLE_MSGSPEC: "1" | ||
| TLLM_ADP_ROUTER_MATCH_RATE_THRESHOLD: "0.10" | ||
| TRTLLM_KV_CACHE_TRANSFER_TIMEOUT_SEC: "600" | ||
| UCX_CUDA_IPC_ENABLE_MNNVL: "y" | ||
| UCX_RNDV_SCHEME: put_zcopy | ||
| TRTLLM_KVCACHE_SEND_BUFFER_COUNT: "1" | ||
| TRTLLM_KVCACHE_RECV_BUFFER_COUNT: "1" | ||
| TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS: "2.61" | ||
| DYN_TRTLLM_ENABLE_ATTENTION_DP: "1" | ||
| DYN_ENGINE_CONV_AFFINITY: "1" | ||
| DYN_TOKENIZER: fastokens | ||
| DYN_PUBLISH_KV_EVENTS: "0" | ||
| decode_environment: *server_environment | ||
| trtllm_config: | ||
| prefill: | ||
| attention_dp_config: | ||
| enable_kv_cache_aware_routing: false | ||
| kv_cache_routing_conversation_affinity: true | ||
| kv_cache_routing_max_sessions: 65536 | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| transceiver_runtime: PYTHON | ||
| kv_cache_bounce_size_mb: 5120 | ||
| max_tokens_in_buffer: 1048576 | ||
| kv_transfer_timeout_ms: 600000 | ||
| cuda_graph_config: null | ||
| disable_overlap_scheduler: false | ||
| enable_attention_dp: true | ||
| enable_chunked_prefill: true | ||
| trust_remote_code: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: true | ||
| event_buffer_max_size: 0 | ||
| free_gpu_memory_fraction: 0.75 | ||
| host_cache_size: 137438953472 | ||
| tokens_per_block: 64 | ||
| max_batch_size: 256 | ||
| max_num_tokens: 8192 | ||
| max_seq_len: 1048576 | ||
| moe_config: | ||
| backend: CUTEDSL | ||
| moe_expert_parallel_size: 4 | ||
| num_postprocess_workers: 8 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| return_perf_metrics: false | ||
| scheduler_config: | ||
| capacity_scheduler_policy: MAX_UTILIZATION | ||
| sparse_attention_config: | ||
| algorithm: dsa | ||
| enable_heuristic_topk: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 5 | ||
| tensor_parallel_size: 4 | ||
| decode: | ||
| cache_transceiver_config: | ||
| backend: NIXL | ||
| transceiver_runtime: PYTHON | ||
| kv_cache_bounce_size_mb: 5120 | ||
| max_tokens_in_buffer: 1048576 | ||
| kv_transfer_timeout_ms: 600000 | ||
| cuda_graph_config: | ||
| batch_sizes: [1] | ||
| enable_padding: true | ||
| enable_attention_dp: false | ||
| trust_remote_code: true | ||
| kv_cache_config: | ||
| dtype: fp8 | ||
| enable_block_reuse: false | ||
| event_buffer_max_size: 0 | ||
| free_gpu_memory_fraction: 0.8 | ||
| tokens_per_block: 64 | ||
| max_batch_size: 1 | ||
| max_num_tokens: 128 | ||
| max_seq_len: 1048576 | ||
| moe_config: | ||
| backend: TRTLLM | ||
| use_low_precision_moe_combine: true | ||
| moe_expert_parallel_size: 1 | ||
| num_postprocess_workers: 4 | ||
| pipeline_parallel_size: 1 | ||
| print_iter_log: true | ||
| return_perf_metrics: false | ||
| sparse_attention_config: | ||
| algorithm: dsa | ||
| enable_heuristic_topk: true | ||
| use_cute_dsl_paged_mqa_logits: true | ||
| use_cute_dsl_topk: true | ||
| speculative_config: | ||
| decoding_type: MTP | ||
| max_draft_len: 5 | ||
| stream_interval: 20 | ||
| tensor_parallel_size: 8 | ||
| publish_events_and_metrics: false | ||
|
|
||
| frontend: | ||
| type: dynamo | ||
| enable_multiple_frontends: false | ||
| env: | ||
| ETCD_LEASE_TTL: '120' | ||
| DYN_ROUTER_QUEUE_THRESHOLD: None | ||
| DYN_ROUTER_TEMPERATURE: '0' | ||
| DYN_TOKENIZER_CACHE: '1' | ||
| DYN_TOKENIZER_CACHE_BYTES: '8000000000' | ||
| DYN_TOKENIZER: fastokens | ||
| DYN_TCP_REQUEST_TIMEOUT: '30' | ||
| DYN_LOG: warn | ||
| DYN_ROUTER_SESSION_AFFINITY_TTL_SECS: '14400' | ||
| args: | ||
| router-mode: kv | ||
| no-kv-events: true | ||
| active-decode-blocks-threshold: None | ||
| active-prefill-tokens-threshold: None | ||
| active-prefill-tokens-threshold-frac: None | ||
| orchestrator_placement: head | ||
|
|
||
| benchmark: | ||
| type: custom | ||
| command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh | ||
| env: | ||
| INFMAX_CONTAINER_WORKSPACE: /infmax-workspace | ||
| RESULT_DIR: /logs/agentic | ||
| PORT: '8000' | ||
| IS_MULTINODE: 'true' | ||
| AIPERF_DYNAMO_SESSION_TIMEOUT_SECONDS: '14400' | ||
| AIPERF_DATASET_MMAP_CACHE_DIR: /aiperf_mmap_cache | ||
| HF_HUB_CACHE: /hf_hub_cache | ||
| WEKA_LOADER_OVERRIDE: semianalysis_cc_traces_weka_062126 | ||
| AIPERF_DATASET_WEKA_LIVE_ASSISTANT_RESPONSES: "0" | ||
| SERVED_MODEL_NAME: GLM-5.2-NVFP4 | ||
| MAX_MODEL_LEN: '1048576' | ||
| AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID: 'true' | ||
| AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: '0' | ||
| OPENAI_API_KEY: EMPTY | ||
| KV_OFFLOADING: dram | ||
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
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 |
|---|---|---|
|
|
@@ -6476,7 +6476,6 @@ | |
| - "Add HiCache host-DRAM KV tier arms at TP4 concurrency 40, 48, 56, and 64 and TP2 concurrency 20, 24, 28, and 32, using hicache ratio 1.5 with write_through, direct io, and page_first_direct layout." | ||
| pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2693 | ||
|
|
||
|
There was a problem hiding this comment. Changelog historical bytes were editedMedium Severity A blank separator line was deleted between existing   Reviewed by Cursor Bugbot for commit 9a3e9c4. Configure here. |
||
| - config-keys: | ||
| - kimik2.6-fp4-b200-dynamo-vllm | ||
| - dsv4-fp4-b200-dynamo-vllm | ||
|
|
@@ -6547,3 +6546,14 @@ | |
| - "Filter AgentX traces at the same 202,752-token context limit used by both TileRT roles so oversized Weka trajectories are excluded before replay." | ||
| - "Pin SemiAnalysisAI/srt-slurm PR #10 commit d1e6c97b3baf3e87103b6d83189544c3c7d61c38, stacked on the AMD/native-router PR #7 and base runtime PR #1, including explicit native HTTP dependencies, GLM-5.1-compatible Transformers v5 router tokenization, incomplete-snapshot recovery, backend-declared conversion GPU resources, pre-container NVIDIA driver-hook activation, and lossless Slurm container-environment exports." | ||
| pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2750 | ||
|
|
||
| - config-keys: | ||
| - glm5.2-fp4-gb300-dynamo-trt-agentic-disagg-mtp | ||
| scenario-type: | ||
| - agentic-coding | ||
| description: | ||
| - "Add a GLM-5.2 concurrency-1 AgentX point using a 1-prefill/1-decode disaggregated topology with TP4 attention-DP prefill and TP8 decode." | ||
| - "Use MTP depth 5 with the committed golden acceptance target, tensor-parallel MoE on decode, and the CUTEDSL top-k path." | ||
| - "Align recipe KV offloading with the master config and keep the benchmark client colocated with the frontend orchestrator." | ||
| - "Add the new concurrency-1 topology to the existing disaggregated configuration key while retaining all published points." | ||
| pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2720 | ||
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.
DRAM offload env vars missing
High Severity
The new recipe sets
KV_OFFLOADINGtodraminbenchmark.env, but omitsKV_OFFLOAD_BACKENDandTOTAL_CPU_DRAM_GB.agentic_srt.shsourcesbenchmark_lib.sh, which exits immediately when DRAM offload is enabled without those variables, so the new concurrency-1 point fails before replay starts. Sibling GLM-5.2 srt-slurm recipes keepKV_OFFLOADINGasnoneand do not take this path.Reviewed by Cursor Bugbot for commit 5e7d158. Configure here.