{"adoption": {"forks": 400, "observed_at": "2026-08-28T04:09:57.922334+00:00", "stars": 7268}, "canonical_url": "https://ross.abutalabs.com/products/streaming-llm", "card": {"archived": false, "artifact_type": "library", "description": "[ICLR 2024] Efficient Streaming Language Models with Attention Sinks", "domain": ["large-language-models", "deep-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 20, "homepage": "https://arxiv.org/abs/2309.17453", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["mit-han-lab/streaming-llm"], "name": "mit-han-lab/streaming-llm", "platform": ["python"], "pushed_at": "2024-07-11T08:14:43+00:00", "repo": "mit-han-lab/streaming-llm", "stars": 7268, "tags": ["attention-sinks", "kv-cache", "streaming-inference", "long-context", "research-paper", "transformers", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["run llm inference on very long or infinite-length inputs", "stream multi-round dialogue without exceeding context window", "reduce kv cache memory usage during llm decoding", "enable window attention to work beyond cache size", "deploy chatbots that can converse indefinitely without crashing"], "what_it_is": "StreamingLLM is a research framework from MIT Han Lab implementing the Attention Sinks method (ICLR 2024) for efficient streaming language model inference. It enables LLMs like Llama-2, MPT, Falcon, and Pythia to handle effectively infinite input lengths without fine-tuning by preserving the KV cache of initial tokens.", "when_to_avoid": ["you need true long-range recall of arbitrary old tokens rather than recent-window coherence", "your model or serving stack is not supported by the attention-sink approach", "you need a production inference server rather than a research codebase"], "when_to_choose": ["you need stable LLM generation over millions of tokens without fine-tuning", "you want memory-efficient streaming inference with a sliding window plus attention sinks", "you use supported models like Llama-2, MPT, Falcon, or Pythia with HuggingFace Transformers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/streaming-llm", "repo": "mit-han-lab/streaming-llm", "role": "main", "score": 27}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:57.922334+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:38:55.984978+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9eed606df41ca8e2831d07f2ae96dd2010a898717b844e8a60234844d371fb47", "fetched_at": "2026-08-28T04:09:57.922334+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/streaming-llm"}, {"content_hash": "0136218468e60eebc1b6ccdf3f282532899d099db8b8aa619e0c528e0e3b9e43", "fetched_at": "2026-08-29T08:34:21.874454+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2309.17453"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:34:21.883480+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:34:21.892075+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:34:21.908496+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:34:21.885148+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 76, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1069, "days_push": 783, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 27, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}