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

feat: support f32 attention output in FA2 template (#799)
Build FlashInfer Docs #516: Commit 32388d0 pushed by yzh119
February 8, 2025 20:15 1m 5s main
February 8, 2025 20:15 1m 5s
Fix the type annotation of q_dtype and kv_dtype on ragged prefill (#798)
Build FlashInfer Docs #515: Commit 824ce40 pushed by abcdabcd987
February 8, 2025 08:26 1m 1s main
February 8, 2025 08:26 1m 1s
bugfix: fix aot build not compatible with cmake command (#796)
Build FlashInfer Docs #514: Commit eb69778 pushed by yzh119
February 7, 2025 19:41 53s main
February 7, 2025 19:41 53s
test: add unittest comparing deepseek prefill fa2 & 3 implementation …
Build FlashInfer Docs #513: Commit 0206ade pushed by yzh119
February 7, 2025 17:49 45s main
February 7, 2025 17:49 45s
bugfix: Fix arguments of plan for split QK/VO head dims (#795)
Build FlashInfer Docs #512: Commit 4127635 pushed by yzh119
February 7, 2025 16:48 51s main
February 7, 2025 16:48 51s
fix rope logic in mla decoding (#793)
Build FlashInfer Docs #511: Commit 504b990 pushed by zhyncs
February 7, 2025 07:00 48s main
February 7, 2025 07:00 48s
bugfix: MLA decode should multiply sm_scale by math::log2e (#787)
Build FlashInfer Docs #510: Commit 23413e0 pushed by yzh119
February 5, 2025 16:00 58s main
February 5, 2025 16:00 58s
refactor: make group_size a part of params (#786)
Build FlashInfer Docs #509: Commit 9569106 pushed by yzh119
February 5, 2025 01:19 47s main
February 5, 2025 01:19 47s
bugfix: drop CTA_TILE_Q=32 (#785)
Build FlashInfer Docs #508: Commit 83bab99 pushed by yzh119
February 4, 2025 20:07 1m 4s main
February 4, 2025 20:07 1m 4s
misc: allow head_dim=64 for sm90 AOT (#783)
Build FlashInfer Docs #507: Commit 2d2e13a pushed by zhyncs
February 4, 2025 20:04 51s main
February 4, 2025 20:04 51s
misc: remove head dimension 64 from AOT (#782)
Build FlashInfer Docs #506: Commit 088e81f pushed by yzh119
February 4, 2025 19:18 45s main
February 4, 2025 19:18 45s
bugfix: fix batch prefill attention kernel unittests (#781)
Build FlashInfer Docs #505: Commit 74a4054 pushed by yzh119
February 4, 2025 19:14 59s main
February 4, 2025 19:14 59s
feat: Separate QK/VO head dim dispatch for sm90 AOT (#778)
Build FlashInfer Docs #504: Commit 1ebbde3 pushed by yzh119
February 4, 2025 06:56 46s main
February 4, 2025 06:56 46s
perf: refactor fa2 prefill template (#776)
Build FlashInfer Docs #503: Commit fc03772 pushed by yzh119
February 4, 2025 05:20 49s main
February 4, 2025 05:20 49s
ci: change whl folder to flashinfer-python (#779)
Build FlashInfer Docs #502: Commit 0ca046a pushed by yzh119
February 4, 2025 04:35 47s main
February 4, 2025 04:35 47s
bugfix: fix the JIT warmup arguments in unittests (#775)
Build FlashInfer Docs #501: Commit c04755e pushed by yzh119
February 1, 2025 21:19 59s main
February 1, 2025 21:19 59s
bugfix: Ensure Loop Termination by Enforcing IEEE-754 Compliance in S…
Build FlashInfer Docs #500: Commit a0443d5 pushed by yzh119
February 1, 2025 21:11 51s main
February 1, 2025 21:11 51s
hotfix: follow up of #772 (#773)
Build FlashInfer Docs #499: Commit 090b100 pushed by yzh119
February 1, 2025 05:34 48s main
February 1, 2025 05:34 48s
refactor: change the structure of attention updater (#772)
Build FlashInfer Docs #498: Commit 3052944 pushed by yzh119
February 1, 2025 05:24 1m 0s main
February 1, 2025 05:24 1m 0s
feat: support deepseek prefill attention shape (#765)
Build FlashInfer Docs #497: Commit eb660de pushed by yzh119
February 1, 2025 03:44 46s main
February 1, 2025 03:44 46s
misc: addressing the package renaming issues (#770)
Build FlashInfer Docs #496: Commit 44ee479 pushed by yzh119
February 1, 2025 01:00 44s main
February 1, 2025 01:00 44s
Version bump: v0.2.0.post2 (#768)
Build FlashInfer Docs #495: Commit 200e954 pushed by yzh119
January 31, 2025 19:48 47s main
January 31, 2025 19:48 47s
bugfix: Fix block-sparse attention API (#767)
Build FlashInfer Docs #494: Commit aeabaf7 pushed by yzh119
January 31, 2025 19:43 46s main
January 31, 2025 19:43 46s
bugfix: use actual sm count for num_sm90_ctas (#762)
Build FlashInfer Docs #493: Commit e5a3bef pushed by yzh119
January 29, 2025 03:30 1m 0s main
January 29, 2025 03:30 1m 0s
fix: match statement not supported in Python 3.8 (#759)
Build FlashInfer Docs #492: Commit 0e25eb2 pushed by yzh119
January 28, 2025 03:42 58s main
January 28, 2025 03:42 58s