{"adoption": {"forks": 64, "observed_at": "2026-08-28T04:03:52.496068+00:00", "stars": 1175}, "canonical_url": "https://ross.abutalabs.com/products/punica", "card": {"archived": false, "artifact_type": "library", "description": "Serving multiple LoRA finetuned LLM as one", "domain": ["large-language-models", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 24, "homepage": "https://arxiv.org/abs/2310.18547", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["punica-ai/punica"], "name": "punica-ai/punica", "platform": ["python"], "pushed_at": "2024-05-08T12:25:17+00:00", "repo": "punica-ai/punica", "stars": 1175, "tags": ["lora", "multi-tenant-serving", "cuda-kernels", "sgmv", "llm-serving", "gpu", "linux"], "topics": ["large-language-models", "llm", "lora"], "urls": [], "use_cases": ["serve multiple LoRA finetuned LLMs on one GPU", "batch requests for different LoRA adapters efficiently", "reduce GPU memory when hosting many finetuned models", "multi-tenant LLM serving with per-user adapters", "benchmark LoRA serving throughput against vLLM or DeepSpeed"], "what_it_is": "Punica is a Python system for serving many LoRA-finetuned LLMs from a single copy of the base model on one GPU, using a custom CUDA kernel (SGMV) to batch LoRA adapter computations. It achieves up to 12x higher throughput than state-of-the-art LLM serving systems for multi-tenant LoRA workloads.", "when_to_avoid": ["you serve only a single model with no LoRA adapters", "you need a production system with active development and broad model support", "you have no CUDA-capable GPU"], "when_to_choose": ["you need to serve many LoRA variants of the same base model cost-effectively", "GPU memory is a bottleneck from loading many finetuned model copies", "your workload mixes requests across different LoRA adapters"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/punica", "repo": "punica-ai/punica", "role": "main", "score": 19}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+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": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+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": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:52.496068+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+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": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+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": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+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": "2026-08-30T06:28:14.289227+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "120d2787e0d995d9d5888fb9be4f490cf80422f22e9cf90b60fc58e8f45eda23", "fetched_at": "2026-08-28T04:03:52.496068+00:00", "kind": "readme", "missing": false, "url": "https://github.com/punica-ai/punica"}, {"content_hash": "4b09fba9121e338e52e17660414281820aed52a683c86da47a92c1ec89628ec0", "fetched_at": "2026-08-29T12:33:32.425651+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2310.18547"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T12:33:32.434612+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T12:33:32.438372+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T12:33:32.441797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T12:33:32.436446+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 79, "rhythm": 8}, "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": 1113, "days_push": 847, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 19, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}