{"adoption": {"forks": 2121, "observed_at": "2026-08-28T04:07:11.785242+00:00", "stars": 2711}, "canonical_url": "https://ross.abutalabs.com/products/vllm-ascend", "card": {"archived": false, "artifact_type": "plugin", "description": "Community maintained hardware plugin for vLLM on Ascend", "domain": ["large-language-models", "artificial-intelligence", "gpu-computing", "developer-tools"], "enriched": true, "function": ["llm-inference", "plugin-system", "machine-learning"], "health_score": 100, "homepage": "https://docs.vllm.ai/projects/ascend", "language": "C++", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["vllm-project/vllm-ascend"], "name": "vllm-project/vllm-ascend", "platform": ["python", "cpp"], "pushed_at": "2026-08-26T14:58:16+00:00", "repo": "vllm-project/vllm-ascend", "stars": 2711, "tags": ["vllm", "ascend-npu", "huawei", "hardware-plugin", "model-serving", "torch-npu", "pd-disaggregation", "speculative-decoding", "linux", "docker", "gpu"], "topics": ["ascend", "inference", "llm", "llm-serving", "llmops", "mlops", "model-serving", "transformer", "vllm"], "urls": [], "use_cases": ["serve llm inference on huawei ascend npu", "run vllm on atlas 800 hardware", "deploy deepseek or qwen models on ascend npus", "set up prefill-decode disaggregation with mooncake", "run multi-node distributed inference with ray on npus", "accelerate decoding with suffix speculative decoding", "serve multimodal llms on non-gpu accelerators"], "what_it_is": "vllm-ascend is a community-maintained hardware plugin that enables vLLM to run large language model inference on Huawei Ascend NPUs. It implements the vLLM hardware-pluggable interface, supporting Transformer, MoE, embedding, and multi-modal models on Atlas hardware.", "when_to_avoid": ["you are running on NVIDIA/AMD GPUs - plain vLLM already supports those natively", "you cannot install the required CANN/TorchNPU software stack", "you need Triton-based features, which are not supported on this backend"], "when_to_choose": ["you have Ascend NPU hardware (Atlas 800 A2/A3, Atlas 300I DUO) and want vLLM serving", "you need PD disaggregation, expert parallelism, or multi-node inference on Ascend", "you want the officially recommended Ascend backend for vLLM"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/vllm-ascend", "repo": "vllm-project/vllm-ascend", "role": "main", "score": 83}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.785242+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:15:35.392827+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25387d25474bb21b871240eb33e7f0d1e99ccc4f0d477812f95bdff4c7389898", "fetched_at": "2026-08-28T04:07:11.785242+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/vllm-ascend"}, {"content_hash": "0c3bd92af16bbe8e9df1c817e7a41832441a460a8719062221d141563f5d7d48", "fetched_at": "2026-08-29T09:58:45.608621+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/ascend"}, {"content_hash": "fad6dd84f837cfbd69e050f174f0859ada7d66923e42e1a3a5a699c0638302db", "fetched_at": "2026-08-29T09:58:45.617827+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/installation.html"}, {"content_hash": "ab4ab23e427d563558d2777056a4149061fd007e26b1626d1854e15826fb483e", "fetched_at": "2026-08-29T09:58:45.620473+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/index.html"}, {"content_hash": "085f81c41e0f2e6b35066ec4a14be96273b603e514a03447c80dfe51a0cd7537", "fetched_at": "2026-08-29T09:58:45.622186+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_colocated_mooncake_multi_instance.html"}, {"content_hash": "8be6c39d663905f7e6e090e5c582628998715eb7b37c44ea107e8dcc9ee50b81", "fetched_at": "2026-08-29T09:58:45.623998+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_single_node.html"}, {"content_hash": "a55e81d79f279b4a0e1e4b85e59863802f3bd0ea817737515c22695f69b22dcb", "fetched_at": "2026-08-29T09:58:45.625805+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/pd_disaggregation_mooncake_multi_node.html"}, {"content_hash": "0610f65f988f85915013cf0326cbf6cab05cbf3cf22fe59e969e7c3c8577b183", "fetched_at": "2026-08-29T09:58:45.627858+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/dynamic_chunked_pipeline_parallel.html"}, {"content_hash": "8e16d746619930378c6e1ecb9d2a3b005c44e8627f6d9c5c845d700478456d8e", "fetched_at": "2026-08-29T09:58:45.629760+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/suffix_speculative_decoding.html"}, {"content_hash": "e13acd3e23168d6d2ccd46ba671af4b0150a12954a1c30d345d87bc1538b628a", "fetched_at": "2026-08-29T09:58:45.631568+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/ascend/en/latest/tutorials/features/ray.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 41, "rhythm": 86}, "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": 581, "days_push": 7, "days_rel": 17, "gap_med": 90.0, "n_releases_24m": 7}, "score": 83, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}