{"adoption": {"forks": 192, "observed_at": "2026-08-28T04:06:14.306550+00:00", "stars": 2111}, "canonical_url": "https://ross.abutalabs.com/products/deepspeed-mii", "card": {"archived": false, "artifact_type": "library", "description": "MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.", "domain": ["large-language-models", "deep-learning", "machine-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "gpu-computing"], "health_score": 50, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["deepspeedai/DeepSpeed-MII"], "name": "deepspeedai/DeepSpeed-MII", "platform": ["python"], "pushed_at": "2025-06-30T16:21:45+00:00", "repo": "deepspeedai/DeepSpeed-MII", "stars": 2111, "tags": ["deepspeed", "text-generation", "continuous-batching", "tensor-parallelism", "kv-cache", "pytorch", "gpu", "linux"], "topics": ["deep-learning", "inference", "pytorch"], "urls": [], "use_cases": ["serve llama-70b with high throughput text generation", "run low-latency llm inference on gpus", "deploy mixtral moe model for inference", "benchmark llm serving throughput against vllm", "generate text from phi-2 efficiently", "reduce cost of llm inference serving"], "what_it_is": "DeepSpeed-MII is a Python library for high-throughput, low-latency large language model inference, built on DeepSpeed. It provides blocked KV-caching, continuous batching, Dynamic SplitFuse, and tensor parallelism with optimized CUDA kernels for serving LLMs like Llama, Mixtral, and Phi.", "when_to_avoid": ["you need multi-vendor GPU or CPU-only inference", "you want the broadest model coverage or largest community (vLLM may fit better)", "you need a fully managed inference service rather than a library"], "when_to_choose": ["you need high-throughput batch text generation with DeepSpeed-optimized kernels", "you want continuous batching and SplitFuse for serving LLMs on NVIDIA GPUs", "you are already in the DeepSpeed ecosystem"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deepspeed-mii", "repo": "deepspeedai/DeepSpeed-MII", "role": "main", "score": 43}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:14.306550+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:53:43.436369+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4eba83b881f05ca5c3d2be2248de84f96b38b4cad237b541804da6726fb57a6c", "fetched_at": "2026-08-28T04:06:14.306550+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepspeedai/DeepSpeed-MII"}, {"content_hash": "d21c4f5a8937bab7f9ccaf7e08d465e6591c3e1ecc4b63290e9bb949ce3269b4", "fetched_at": "2026-08-29T10:33:45.046319+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/deepspeed-mii/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 29, "longevity": 100, "rhythm": 28}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1624, "days_push": 429, "days_rel": 526, "gap_med": 72.5, "n_releases_24m": 3}, "score": 43, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}