{"full_name":"lucidrains/x-transformers","owner":"lucidrains","name":"x-transformers","shard":"1","url":"https://github.com/lucidrains/x-transformers","description":"A concise but complete full-attention transformer with a set of promising experimental features from various papers","homepage":"","topics":["artificial-intelligence","deep-learning","attention-mechanism","transformers"],"tag_pages":["artificial-intelligence","attention-mechanism","deep-learning","transformers"],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/108653?u=6d8a8e8d28f8512933d729d7503ae3e622d59c64&v=4","created_at":"2020-10-24T22:13:25Z","pushed_at":"2026-11-11T15:08:55Z","metrics":{"stars":5961,"forks":532,"watchers":53,"issues":281,"prs":144,"releases":606,"issues_open":79,"issues_closed":202,"prs_open":54,"prs_closed":25,"prs_merged":65,"discussions":0},"growth":{"day":{"stars":0,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[5963,5964,5964,5964,5963,5961,5961],"forks":[531,532,532,532,532,532,532],"watchers":[null,53,53,53,53,53,53],"issues_open":[null,79,79,79,79,79,79],"prs_open":[null,44,44,54,54,54,54]},"boards":{},"same_owner":[{"full_name":"lucidrains/DALLE-pytorch","name":"DALLE-pytorch","shard":"1","boards":{}}],"issues":[{"number":159,"title":"How to use the rope scaling with x_transformers ?","comments":21,"created_at":"2023-06-29T16:26:36Z"},{"number":166,"title":"Feature request: support return_mems in ContinuousTransformerWrapper","comments":16,"created_at":"2023-07-17T15:02:14Z"},{"number":212,"title":"ONNX export failed","comments":14,"created_at":"2023-11-27T11:01:41Z"},{"number":21,"title":"Any tips for speeding up generation?","comments":14,"created_at":"2021-03-11T09:57:33Z"},{"number":143,"title":"RuntimeError: No available kernel.  Aborting execution.","comments":12,"created_at":"2023-05-12T18:43:23Z"},{"number":292,"title":"Support for a mask during autoregressive generation with Key-Value Caching","comments":10,"created_at":"2024-11-12T19:54:29Z"},{"number":332,"title":"Question: `prepend_embeds` & `prepend_mask` + KV caching","comments":8,"created_at":"2025-06-26T03:05:19Z"},{"number":70,"title":"Absolute positional embedding present with ALiBi relative positional encoding.","comments":7,"created_at":"2021-11-28T11:56:58Z"}],"discussions":[],"latest_release":{"name":"2.16.1","tag":"2.16.1","published_at":"2026-02-12T16:25:41Z","body":"## What's Changed\n* Support efficient flash attention for packed sequences using flash-attn-2.0 by @muthissar in https://github.com/lucidrains/x-transformers/pull/350\n\n## New Contributors\n* @muthissar made their first contribution in https://github.com/lucidrains/x-transformers/pull/350\n\n**Full Changelog**: https://github.com/lucidrains/x-transformers/compare/2.16.0...2.16.1","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}