# Qwen Flash-Next: SGLang concurrency and latency One 128 GB unified-memory DGX Spark serves senfu NVFP4 at its full recorded revision through SGLang commit 4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b. The recipe keeps PLE on NVMe through mmap, uses an FP8 dense path and an NVFP4 LM head, and disables MTP. The repository documentation pin is separate from the engine and weight revisions. - Type: Performance report - Evidence: source_reported; site reproduced: false - Model family: Qwen - Model: senfu/Qwen3.8-Flash-Next-NVFP4 - Original author: nabe2030 - Original project: https://github.com/nabe2030/flashnext-dgx-spark - Pinned document: https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/README.md - Source revision: 8a161f2bee2e2d85b689a2d457ae68bead3929a4 - Source commit time (not experiment date): 2026-09-21T10:13:50Z - Checked: 2026-10-18 - Experiment date: None - Runtime topics: SGLang - Hardware topics: spark, nvidia - Reported setup: {"system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "parallelism": null, "kv_dtype": null, "context_limit_tokens": null, "experiment_date": null} - Performance figures: attributed selections with per-point conditions; no cross-source ranking ## Conditions Unknown is null. Recipe options are not measured benchmark settings. ```json { "conditions": { "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "weight_hash": null, "runtime_execution_revision": null, "input_tokens": null, "output_tokens": null, "concurrency": null, "cache_state": null, "quantization": null, "speculative_decoding": null, "temperature": null, "top_p": null }, "test_profiles": [ { "label": "single Spark senfu C1 aggregate_output_rate", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" } }, { "label": "single Spark senfu C1 median_ttft", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" } }, { "label": "single Spark senfu C1 median_time_per_output_token", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" } }, { "label": "single Spark senfu C8 aggregate_output_rate", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C8 median_ttft", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C8 median_time_per_output_token", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C16 aggregate_output_rate", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C16 median_ttft", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C16 median_time_per_output_token", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C32 aggregate_output_rate", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C32 median_ttft", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" } }, { "label": "single Spark senfu C32 median_time_per_output_token", "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12", "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" } } ], "recipe_parameters": null, "deployment_options": [] } ``` ## Reading notes - One source document can contain different experiments and versions; not an independent experiment count. ## Limits - No independent site model execution. - Missing sampling, exact executed image digests and measurement boundaries remain null. - Configured window, completed input, scheduler ceiling and measured full-window concurrency are separate quantities. ## License declaration {"declared_spdx": "apache-2.0", "scope": "Source declaration; models, runtime and dependencies retain their exact terms."} ## Editorial answer One 128 GB unified-memory DGX Spark serves senfu NVFP4 at its full recorded revision through SGLang commit 4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b. The recipe keeps PLE on NVMe through mmap, uses an FP8 dense path and an NVFP4 LM head, and disables MTP. The repository documentation pin is separate from the engine and weight revisions. By Run AI Here editorial ยท 2026-10-18 Original source-based interpretation; local Spark Qwen draft with Codex factual review, no site model benchmark. ## Which checkpoint and runtime were tested? One 128 GB unified-memory DGX Spark serves senfu NVFP4 at its full recorded revision through SGLang commit 4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b. The recipe keeps PLE on NVMe through mmap, uses an FP8 dense path and an NVFP4 LM head, and disables MTP. The repository documentation pin is separate from the engine and weight revisions. Sources: https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/README.md ## What workload defines the concurrency curve? The selected ShareGPT-200 sweep uses vllm bench serve, thinking off and explicitly disabled radix caching, after one discarded warmup request. C1 is the median of three trials; C8, C16 and C32 are single trials. Exact prompt/output distributions, sampling and per-sweep window are not reported. All selected senfu trials completed 200 requests without errors. Sources: https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md ## How should throughput and latency be read together? Aggregate output rises with concurrency, while the reported median TTFT and time per output token also rise. Read all three metrics with their own timing definitions. Dividing aggregate rate by concurrency does not reconstruct a measured individual stream. Single high-load trials provide no variability estimate, and results from another checkpoint or engine cannot isolate a pure scheduler effect. Sources: https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md ## Does the recipe prove simultaneous long windows? The 49152-token window, 393216 total tokens and eight slots describe one published long-context configuration, not a saved all-slots-full workload. The separate 3.04 GB KV allocation at 128K keeps the original GB label; it is not whole-model peak RAM. The source reports 128K stability but supplies no complete long-request latency or memory series for every concurrency level. Sources: https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/README.md ## Selected source-reported figures Each point retains its own configuration, measurement unit and source. No site reproduction or cross-source ranking. ```json [ { "label": "single Spark senfu C1 aggregate_output_rate", "metric": "aggregate_output_rate", "value": 26.97, "unit": "tokens/s", "statistic": "median of three trials", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 9, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9" }, { "label": "single Spark senfu C1 median_ttft", "metric": "median_ttft", "value": 221.23, "unit": "ms", "statistic": "median of three trials", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 9, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9" }, { "label": "single Spark senfu C1 median_time_per_output_token", "metric": "median_time_per_output_token", "value": 36.14, "unit": "ms", "statistic": "median of three trials", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 1, "repetitions": 3, "summary_kind": "median of three trials" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 9, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L9" }, { "label": "single Spark senfu C8 aggregate_output_rate", "metric": "aggregate_output_rate", "value": 67.68, "unit": "tokens/s", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 10, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10" }, { "label": "single Spark senfu C8 median_ttft", "metric": "median_ttft", "value": 526.78, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 10, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10" }, { "label": "single Spark senfu C8 median_time_per_output_token", "metric": "median_time_per_output_token", "value": 113.46, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 8, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 10, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L10" }, { "label": "single Spark senfu C16 aggregate_output_rate", "metric": "aggregate_output_rate", "value": 77.48, "unit": "tokens/s", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 11, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11" }, { "label": "single Spark senfu C16 median_ttft", "metric": "median_ttft", "value": 686.27, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 11, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11" }, { "label": "single Spark senfu C16 median_time_per_output_token", "metric": "median_time_per_output_token", "value": 198.0, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 16, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 11, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L11" }, { "label": "single Spark senfu C32 aggregate_output_rate", "metric": "aggregate_output_rate", "value": 89.35, "unit": "tokens/s", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 12, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12" }, { "label": "single Spark senfu C32 median_ttft", "metric": "median_ttft", "value": 1017.98, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 12, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12" }, { "label": "single Spark senfu C32 median_time_per_output_token", "metric": "median_time_per_output_token", "value": 343.57, "unit": "ms", "statistic": "single trial", "uncertainty": null, "conditions": { "model": "Qwen3.8-Flash-Next", "model_artifact": "senfu/Qwen3.8-Flash-Next-NVFP4", "model_revision": "5d37b3b3711d8406174b96ff950c0aa16324b266", "engine": "SGLang", "runtime_execution_revision": "4fb9b5b5bad41ac7de5586ec812c421fe3aa2b8b", "executed_image_digest": null, "system": "one DGX Spark GB10, 128 GB unified memory; NVMe file-backed PLE", "node_count": 1, "weight_precision": "NVFP4 experts and LM head; FP8 dense path", "kv_dtype": null, "draft_tokens": 0, "thinking": false, "temperature": null, "top_p": null, "input_tokens": null, "output_tokens": null, "actual_output_tokens": null, "request_count": 200, "cache_state": "radix/prefix cache explicitly disabled; one warmup discarded", "harness": "vllm bench serve, ShareGPT 200 prompts", "experiment_date": null, "context_limit_tokens": null, "executed_context_for_each_sweep_unreported": true, "PLE_backing": "NVMe mmap", "exact_prompt_and_output_distributions_unreported": true, "concurrency": 32, "repetitions": 1, "summary_kind": "single trial" }, "evidence_state": "source_reported", "site_reproduced": false, "source_document_id": "qwen-sglang-results", "source_document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "source_line": 12, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md#L12" } ] ``` ## Supplemental source identities ```json { "supplemental_sources": [ { "document_id": "qwen-sglang-results", "parent_record_id": "qwen38-flash-next-sglang-concurrency", "publisher": "nabe2030", "repository": "nabe2030/flashnext-dgx-spark", "revision": "8a161f2bee2e2d85b689a2d457ae68bead3929a4", "document_path": "results/speed_senfu_vs_radixark.md", "pinned_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/results/speed_senfu_vs_radixark.md", "document_sha256": "cf77f1feb1a37ab7fcdd8073ca0ff3b5fe78b8c47cf261fd917ae69fcb018297", "checked_on": "2026-10-18" } ] } ``` ## memory observations ```json { "memory_observations": [ { "kind": "source_reported_KV_allocation_at_context", "context_limit_tokens": 131072, "KV_source_GB": 3.04, "GB_byte_convention_verified": false, "whole_model_peak_RAM": null, "source_document_id": "qwen-sglang-readme", "source_document_sha256": "8a27445102511702ff42fa60cfcc469583de37c4c0bd031c43cd40db7c0db9f4", "source_line": 19, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/README.md#L19" }, { "kind": "source_recipe_slots_not_a_completed_long_batch", "per_request_window_tokens": 49152, "shared_total_tokens": 393216, "request_slots": 8, "all_slots_full_simultaneously_proven": false, "source_document_id": "qwen-sglang-readme", "source_document_sha256": "8a27445102511702ff42fa60cfcc469583de37c4c0bd031c43cd40db7c0db9f4", "source_line": 134, "evidence_url": "https://github.com/nabe2030/flashnext-dgx-spark/blob/8a161f2bee2e2d85b689a2d457ae68bead3929a4/README.md#L134" } ] } ```