{"adoption": {"forks": 167, "observed_at": "2026-08-28T04:04:58.365279+00:00", "stars": 1526}, "canonical_url": "https://ross.abutalabs.com/products/triton-distributed", "card": {"archived": false, "artifact_type": "library", "description": "Distributed Compiler and Optimized Parallel Kernels", "domain": ["gpu-computing", "microservices", "deep-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["compiler", "gpu-computing", "machine-learning", "llm-training", "benchmarking"], "health_score": 93, "homepage": "https://triton-distributed.readthedocs.io/en/latest/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["ByteDance-Seed/Triton-distributed"], "name": "ByteDance-Seed/Triton-distributed", "platform": ["python"], "pushed_at": "2026-08-12T09:46:35+00:00", "repo": "ByteDance-Seed/Triton-distributed", "stars": 1526, "tags": ["triton", "distributed-kernels", "computation-communication-overlap", "moe", "expert-parallelism", "nvidia-gpu", "amd-gpu", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["write distributed GPU kernels with computation-communication overlap", "implement expert parallelism for MoE models", "build low-latency all-to-all communication kernels", "optimize GEMM operations across multiple GPUs", "profile intra-kernel performance on GPUs", "port distributed kernel compilation to custom hardware"], "what_it_is": "Triton-distributed is a distributed compiler built on OpenAI Triton for computation-communication overlapping on multi-GPU systems. It lets developers write high-performance distributed kernels comparable to hand-optimized libraries like Distributed-GEMM and FLUX, targeting Nvidia and AMD GPUs.", "when_to_avoid": ["you only need single-GPU kernels (plain Triton suffices)", "you want a turnkey distributed training framework rather than a kernel compiler", "you target CPUs or non-GPU accelerators without porting effort"], "when_to_choose": ["you need custom distributed kernels beyond what standard Triton offers", "you are training or serving large models with expert parallelism", "you want Python-level kernel development instead of CUDA/CUTLASS", "you need computation and communication to overlap in a single kernel"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/triton-distributed", "repo": "ByteDance-Seed/Triton-distributed", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.365279+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.335649+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "15a5df77389629749659c4af8a4015bb4cf8c05ff9809396bec4fa501a3d9961", "fetched_at": "2026-08-28T04:04:58.365279+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ByteDance-Seed/Triton-distributed"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 37, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["prerelease_only"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 518, "days_push": 21, "days_rel": 355, "gap_med": 31.0, "n_releases_24m": 3}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}