{"adoption": {"forks": 121, "observed_at": "2026-08-28T04:05:29.743149+00:00", "stars": 1738}, "canonical_url": "https://ross.abutalabs.com/products/tilert", "card": {"archived": false, "artifact_type": "library", "description": "Tile-Based Runtime for Ultra-Low-Latency LLM Inference", "domain": ["large-language-models", "deep-learning", "gpu-computing", "performance"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 98, "homepage": "https://www.tilert.ai", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["tile-ai/TileRT"], "name": "tile-ai/TileRT", "platform": ["python"], "pushed_at": "2026-08-13T13:21:51+00:00", "repo": "tile-ai/TileRT", "stars": 1738, "tags": ["inference-runtime", "low-latency", "decode-optimization", "multi-token-prediction", "pd-disaggregation", "vllm-integration", "linux", "gpu", "docker"], "topics": [], "urls": [], "use_cases": ["run frontier LLMs with millisecond single-stream decode latency", "serve GLM-5 or DeepSeek-V3.2 at 500-1000+ tokens/s", "combine vLLM prefill with TileRT decode via PD disaggregation", "use multi-token prediction to boost decoding throughput", "sustain high tokens/s at very long context lengths up to 200K"], "what_it_is": "TileRT is a tile-based runtime for ultra-low-latency LLM inference, achieving hundreds to over 1000 tokens/s decode speeds on frontier models like DeepSeek-V3.2 and GLM-5 using model-system co-design on multi-GPU nodes. It integrates with vLLM via prefill-decode disaggregation behind an OpenAI-compatible endpoint.", "when_to_avoid": ["you need broad model coverage beyond the supported GLM/DeepSeek/MiMo models", "you need a general-purpose serving stack with heavy multi-user batching", "you run on non-NVIDIA hardware or small consumer GPUs"], "when_to_choose": ["you need maximum single-stream decode speed for large MoE models on NVIDIA GPUs", "you want an OpenAI-compatible endpoint with vLLM prefill and TileRT decode", "you are building latency-sensitive agentic or real-time applications"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tilert", "repo": "tile-ai/TileRT", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.743149+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:30:37.131662+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d657b2a9f0fda3f2fd2540b955673c2bf7c9550319ac0ec122f9df44ee765499", "fetched_at": "2026-08-28T04:05:29.743149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tile-ai/TileRT"}, {"content_hash": "604707136d24126308fc0a04ff16ecde8d3efc2ba2abefdd602066b8123424d6", "fetched_at": "2026-08-29T11:07:44.203317+00:00", "kind": "homepage", "missing": false, "url": "https://www.tilert.ai"}, {"content_hash": "6ea12521253c013c347be4302046207c231bf640d542dc77e81b2f6a8d4fd06a", "fetched_at": "2026-08-29T11:07:44.205709+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tilert/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 21, "rhythm": 84}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 295, "days_push": 20, "days_rel": 27, "gap_med": 33, "n_releases_24m": 6}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}