Skip to content

Actions: flashinfer-ai/flashinfer

Build FlashInfer Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
406 workflow runs
406 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ci: setup pre-commit (#584)
Build FlashInfer Docs #381: Commit 979bb6c pushed by yzh119
November 5, 2024 07:56 1m 3s main
November 5, 2024 07:56 1m 3s
add benchmark for append_paged_kv_cache (#583)
Build FlashInfer Docs #380: Commit e5cafde pushed by zhyncs
November 5, 2024 05:53 51s main
November 5, 2024 05:53 51s
misc: simplifying sampilng data structures (#581)
Build FlashInfer Docs #379: Commit c3572de pushed by yzh119
November 4, 2024 22:14 53s main
November 4, 2024 22:14 53s
bugfix: symlinks not set up properly in setup.py (#580)
Build FlashInfer Docs #378: Commit 98a5483 pushed by yzh119
November 2, 2024 02:41 1m 36s main
November 2, 2024 02:41 1m 36s
bugfix: workspace dir when no GPU is available (#579)
Build FlashInfer Docs #377: Commit c83cd6c pushed by yzh119
November 2, 2024 02:41 1m 11s main
November 2, 2024 02:41 1m 11s
misc: return type overload for return_lse (#578)
Build FlashInfer Docs #376: Commit fc0f6d4 pushed by yzh119
November 2, 2024 02:40 57s main
November 2, 2024 02:40 57s
feat: support MLA decode (#551)
Build FlashInfer Docs #375: Commit 5d454ed pushed by yzh119
November 2, 2024 02:39 54s main
November 2, 2024 02:39 54s
doc: fix sphinx (#573)
Build FlashInfer Docs #374: Commit 06a922f pushed by yzh119
October 31, 2024 08:54 44s main
October 31, 2024 08:54 44s
fix broken cpp integration caused by #567 (#572)
Build FlashInfer Docs #373: Commit f19e308 pushed by zhyncs
October 30, 2024 12:54 49s main
October 30, 2024 12:54 49s
refactor: Refactor JIT and AOT build script (#567)
Build FlashInfer Docs #372: Commit 7df90dd pushed by yzh119
October 30, 2024 07:20 57m 1s main
October 30, 2024 07:20 57m 1s
bugfix: fix broken cpp integration caused by #553 (#570)
Build FlashInfer Docs #371: Commit e46d9a7 pushed by yzh119
October 30, 2024 05:29 37s main
October 30, 2024 05:29 37s
feat: torch custom_op fix for rope (#569)
Build FlashInfer Docs #370: Commit 3e104bc pushed by yzh119
October 30, 2024 02:35 43s main
October 30, 2024 02:35 43s
feat: support huggingface transformer style rope interface (#568)
Build FlashInfer Docs #369: Commit 4f40420 pushed by yzh119
October 29, 2024 21:51 39s main
October 29, 2024 21:51 39s
Change workspace dir (#566)
Build FlashInfer Docs #368: Commit cdc12c3 pushed by yzh119
October 29, 2024 20:15 47s main
October 29, 2024 20:15 47s
bugfix: do not use non-blocking copy for gpu to cpu transfer (#564)
Build FlashInfer Docs #367: Commit d30667b pushed by yzh119
October 27, 2024 09:46 41s main
October 27, 2024 09:46 41s
bugfix: fix the sliding window iteration bound for SWA in batch prefi…
Build FlashInfer Docs #366: Commit 4800368 pushed by yzh119
October 27, 2024 09:38 41s main
October 27, 2024 09:38 41s
bugfix: bugfix for torch library annotation (#562)
Build FlashInfer Docs #365: Commit 9d2996d pushed by yzh119
October 26, 2024 23:20 50s main
October 26, 2024 23:20 50s
perf: remove unnecessary contiguous operation in block sparse attenti…
Build FlashInfer Docs #364: Commit 7a7ad46 pushed by yzh119
October 26, 2024 22:02 46s main
October 26, 2024 22:02 46s
perf: use cuda-core implemention for io-bound block-sparse attention …
Build FlashInfer Docs #363: Commit 3fbf028 pushed by yzh119
October 26, 2024 21:37 36s main
October 26, 2024 21:37 36s
bugfix: fix batch_prefill.cu in AOT mode after #554 (#559)
Build FlashInfer Docs #362: Commit ea86f81 pushed by yzh119
October 26, 2024 21:29 40s main
October 26, 2024 21:29 40s
feat: add group size 3 to GQA decode dispatch (#558)
Build FlashInfer Docs #361: Commit 6227562 pushed by yzh119
October 25, 2024 19:48 50s main
October 25, 2024 19:48 50s
misc: typing improvement (#555)
Build FlashInfer Docs #360: Commit 9e10936 pushed by yzh119
October 25, 2024 02:54 47s main
October 25, 2024 02:54 47s
feat: torch.compile and custom_op support (#554)
Build FlashInfer Docs #359: Commit 9bf916f pushed by yzh119
October 25, 2024 02:51 49s main
October 25, 2024 02:51 49s
bugfix: fix block sparse wrappers (#556)
Build FlashInfer Docs #358: Commit 2989556 pushed by yzh119
October 25, 2024 02:39 46s main
October 25, 2024 02:39 46s
feat: non-contiguous query with paged kv cache (#553)
Build FlashInfer Docs #357: Commit 89f2c4a pushed by yzh119
October 25, 2024 02:09 2m 40s main
October 25, 2024 02:09 2m 40s