{"adoption": {"forks": 165, "observed_at": "2026-09-03T02:15:06.654273+00:00", "stars": 1176}, "canonical_url": "https://ross.abutalabs.com/products/deepseek-v4-flash-dspark-2x-dgx-spark", "card": {"archived": false, "artifact_type": "infra-config", "description": "DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks", "domain": ["large-language-models", "gpu-computing", "self-hosted", "infrastructure-as-code"], "enriched": true, "function": ["llm-inference", "deployment", "gpu-computing", "developer-tools"], "health_score": 80, "homepage": "https://x.com/MiaAI_lab", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"], "name": "MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark", "platform": ["self-hosted", "python"], "pushed_at": "2026-09-02T19:54:34+00:00", "repo": "MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark", "stars": 1176, "tags": ["vllm", "dgx-spark", "speculative-decoding", "deepseek", "multi-node", "tensor-parallelism", "recipe", "linux", "docker", "gpu"], "topics": [], "urls": [], "use_cases": ["serve deepseek v4 flash on two dgx spark nodes", "run vllm with tensor parallelism across multiple machines", "set up speculative decoding for faster llm inference", "deploy a large language model on a small gpu cluster", "configure nccl networking for multi-node inference", "self-host deepseek models with 1m token context"], "what_it_is": "A deployment recipe for serving DeepSeek-V4-Flash-0731 across two NVIDIA DGX Spark nodes using vLLM with tensor parallelism and DSpark speculative decoding. It provides environment configuration, weight caching scripts, and validation tooling for a two-node inference cluster.", "when_to_avoid": ["you have a single GPU or non-DGX hardware", "you need training or fine-tuning rather than inference", "you want a general-purpose serving stack rather than a model-specific recipe"], "when_to_choose": ["you own two DGX Spark devices and want a tested serving recipe", "you need high-throughput DeepSeek V4 Flash inference with long context", "you want preconfigured vLLM multi-node deployment scripts"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deepseek-v4-flash-dspark-2x-dgx-spark", "repo": "MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:06.654273+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:13:41.869514+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dad0c7cd78e6e0fdaebc0baabfa944224bbe2b2a34fc2d714cfc90dd939c10a8", "fetched_at": "2026-09-03T02:15:06.654273+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 4, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 66, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}