Skip to content

Actions: flashinfer-ai/flashinfer

Build FlashInfer Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
572 workflow runs
572 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

perf: use 1x4 warp layout for small query length (#322)
Build FlashInfer Docs #191: Commit 4e89b4d pushed by yzh119
June 21, 2024 18:44 1m 0s main
June 21, 2024 18:44 1m 0s
ci: use python3 for release wheel workflow (#321)
Build FlashInfer Docs #190: Commit 231b1dc pushed by yzh119
June 20, 2024 16:25 56s main
June 20, 2024 16:25 56s
ci: fix setuptools version (#319)
Build FlashInfer Docs #189: Commit a0297e7 pushed by yzh119
June 20, 2024 08:54 57s main
June 20, 2024 08:54 57s
chore(main): release 0.0.5 (#232)
Build FlashInfer Docs #188: Commit 5c05676 pushed by yzh119
June 20, 2024 08:41 52s main
June 20, 2024 08:41 52s
doc: bump doc version to v0.0.5 (#318)
Build FlashInfer Docs #187: Commit 62cd10d pushed by yzh119
June 20, 2024 08:16 46s main
June 20, 2024 08:16 46s
feat: add use_tensor_cores option to decode kernels to accelerate G…
Build FlashInfer Docs #186: Commit 3b50dd5 pushed by yzh119
June 20, 2024 08:14 46s main
June 20, 2024 08:14 46s
bugfix: fix cascade test (#315)
Build FlashInfer Docs #185: Commit 2ef20c1 pushed by yzh119
June 20, 2024 06:53 47s main
June 20, 2024 06:53 47s
perf: split kv-cache for prefill/append kernels (#310)
Build FlashInfer Docs #184: Commit f0bb0a3 pushed by yzh119
June 20, 2024 06:47 54s main
June 20, 2024 06:47 54s
refactor: simplify kernel interface (#312)
Build FlashInfer Docs #183: Commit cf77d96 pushed by yzh119
June 18, 2024 09:47 48s main
June 18, 2024 09:47 48s
perf: use packed bit array for attention mask (#308)
Build FlashInfer Docs #182: Commit 3d43dc9 pushed by yzh119
June 16, 2024 07:50 47s main
June 16, 2024 07:50 47s
refactor: use combined div/mod for write lse (#307)
Build FlashInfer Docs #181: Commit 876cc53 pushed by yzh119
June 15, 2024 23:55 40s main
June 15, 2024 23:55 40s
refactor: remove page_size from template parameters for prefill ker…
Build FlashInfer Docs #180: Commit 82fd8c7 pushed by yzh119
June 15, 2024 20:30 1m 0s main
June 15, 2024 20:30 1m 0s
ci: faster compile/ci (#305)
Build FlashInfer Docs #179: Commit 955dfc5 pushed by yzh119
June 15, 2024 18:04 46s main
June 15, 2024 18:04 46s
test: fix fp8 calibration test (#303)
Build FlashInfer Docs #178: Commit c507156 pushed by yzh119
June 15, 2024 08:20 43s main
June 15, 2024 08:20 43s
test: fix unittest for group gemm (#302)
Build FlashInfer Docs #177: Commit 51fccf6 pushed by yzh119
June 15, 2024 07:07 56s main
June 15, 2024 07:07 56s
rafactor: move gqa_group_size from template parameter to input argu…
Build FlashInfer Docs #176: Commit c111ca6 pushed by yzh119
June 15, 2024 06:44 43s main
June 15, 2024 06:44 43s
doc: fix logits cap docstring (#300)
Build FlashInfer Docs #175: Commit bb1783b pushed by yzh119
June 14, 2024 09:39 57s main
June 14, 2024 09:39 57s
doc: fix the description of logits cap in docstring (#299)
Build FlashInfer Docs #174: Commit c18745b pushed by yzh119
June 14, 2024 09:36 42s main
June 14, 2024 09:36 42s
feat: initial support of logits hook (#298)
Build FlashInfer Docs #173: Commit ab1e2ad pushed by yzh119
June 14, 2024 09:13 56s main
June 14, 2024 09:13 56s
feat: Separate Q and KV dtypes for decode (#286)
Build FlashInfer Docs #172: Commit 5602659 pushed by yzh119
June 13, 2024 23:47 43s main
June 13, 2024 23:47 43s
bugfix: suppress alignment warning of sampling kernels (#297)
Build FlashInfer Docs #171: Commit 1250b68 pushed by yzh119
June 11, 2024 08:47 45s main
June 11, 2024 08:47 45s
bugfix: fix wrong padded_batch_size_ (#296)
Build FlashInfer Docs #170: Commit aff4cf0 pushed by yzh119
June 11, 2024 05:14 1m 11s main
June 11, 2024 05:14 1m 11s
refactor: refactor decode handler (#294)
Build FlashInfer Docs #169: Commit 60459e4 pushed by yzh119
June 10, 2024 10:33 53s main
June 10, 2024 10:33 53s
misc: add some notes in cmake.config (#293)
Build FlashInfer Docs #168: Commit 4c5e28b pushed by yzh119
June 10, 2024 07:20 45s main
June 10, 2024 07:20 45s
doc: fix the math display of group gemm operator (#292)
Build FlashInfer Docs #167: Commit 4198686 pushed by yzh119
June 10, 2024 07:14 57s main
June 10, 2024 07:14 57s
ProTip! You can narrow down the results and go further in time using created:<2024-06-10 or the other filters available.