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

hotfix: fix the bug in #386 (#387)
Build FlashInfer Docs #241: Commit dc3f184 pushed by yzh119
July 21, 2024 00:32 44s main
July 21, 2024 00:32 44s
bugfix: fix sampling API's behavior on cu118 (#386)
Build FlashInfer Docs #240: Commit 0cd4994 pushed by yzh119
July 21, 2024 00:24 44s main
July 21, 2024 00:24 44s
chore(main): release 0.1.1 (#381)
Build FlashInfer Docs #239: Commit b64d5c9 pushed by yzh119
July 20, 2024 09:15 48s main
July 20, 2024 09:15 48s
bugfix: Fix invalid kernel configuration for sm86 (#385)
Build FlashInfer Docs #238: Commit cdac577 pushed by yzh119
July 20, 2024 09:09 43s main
July 20, 2024 09:09 43s
feat: expose decoupled kv-cache to pytorch api (#383)
Build FlashInfer Docs #237: Commit 457a0ae pushed by yzh119
July 20, 2024 01:25 52s main
July 20, 2024 01:25 52s
perf: use stmatrix in epilogue for sm90+ (#380)
Build FlashInfer Docs #236: Commit c6f20d1 pushed by yzh119
July 19, 2024 02:43 43s main
July 19, 2024 02:43 43s
refactor: decouple kv-cache storage (#379)
Build FlashInfer Docs #235: Commit d68a408 pushed by yzh119
July 18, 2024 08:38 51s main
July 18, 2024 08:38 51s
doc: update documentation to v0.1.0 (#378)
Build FlashInfer Docs #234: Commit 9cb28de pushed by yzh119
July 18, 2024 05:50 54s main
July 18, 2024 05:50 54s
chore(main): release 0.1.0 (#373)
Build FlashInfer Docs #233: Commit 58b68d0 pushed by yzh119
July 17, 2024 08:29 1m 10s main
July 17, 2024 08:29 1m 10s
feat: expose pytorch api for block sparse attention (#375)
Build FlashInfer Docs #232: Commit 4bba6fa pushed by yzh119
July 17, 2024 08:28 1m 3s main
July 17, 2024 08:28 1m 3s
doc: fix typo (#376)
Build FlashInfer Docs #231: Commit b2d5994 pushed by yzh119
July 13, 2024 18:31 1m 4s main
July 13, 2024 18:31 1m 4s
feat: Fused GPU sampling kernel for joint top-k & top-p sampling (#374)
Build FlashInfer Docs #230: Commit 6e028eb pushed by yzh119
July 13, 2024 03:43 44s main
July 13, 2024 03:43 44s
feat: Add mask to merge_state_in_place (#372)
Build FlashInfer Docs #229: Commit e14fa81 pushed by yzh119
July 13, 2024 02:09 57s main
July 13, 2024 02:09 57s
chore(main): release 0.0.9 (#359)
Build FlashInfer Docs #228: Commit 17a5f1b pushed by yzh119
July 12, 2024 05:54 46s main
July 12, 2024 05:54 46s
refactor: reduce binary size by making kv_layout an argument instea…
Build FlashInfer Docs #227: Commit 024a79f pushed by yzh119
July 12, 2024 05:31 44s main
July 12, 2024 05:31 44s
bugfix: fix the decode kernel segfault in cudagraph mode (#368)
Build FlashInfer Docs #226: Commit c69cfab pushed by yzh119
July 11, 2024 06:16 1m 4s main
July 11, 2024 06:16 1m 4s
perf: accelerate alibi (#365)
Build FlashInfer Docs #225: Commit 4f0a9f9 pushed by yzh119
July 10, 2024 23:10 1m 18s main
July 10, 2024 23:10 1m 18s
perf: Optimize tensor conversions in C++ code to avoid unnecessary co…
Build FlashInfer Docs #224: Commit 1116237 pushed by yzh119
July 10, 2024 23:10 46s main
July 10, 2024 23:10 46s
refactor: slight refactor of prefill kernels (#364)
Build FlashInfer Docs #223: Commit 264082e pushed by yzh119
July 10, 2024 08:22 1m 3s main
July 10, 2024 08:22 1m 3s
bugfix: fix decode kernels output for empty kv cache (#363)
Build FlashInfer Docs #222: Commit ac72b1c pushed by yzh119
July 10, 2024 07:01 54s main
July 10, 2024 07:01 54s
bugfix: check gpu id in PyTorch APIs and use input tensor's gpu defau…
Build FlashInfer Docs #221: Commit 1b84fab pushed by yzh119
July 6, 2024 20:25 47s main
July 6, 2024 20:25 47s
docs: fix CHANGELOG link (#360)
Build FlashInfer Docs #220: Commit 3536198 pushed by yzh119
July 4, 2024 18:00 1m 6s main
July 4, 2024 18:00 1m 6s
perf: accelerate gqa performance (#356)
Build FlashInfer Docs #219: Commit e56ddad pushed by yzh119
July 4, 2024 07:57 55s main
July 4, 2024 07:57 55s
Fix doc typo (#357)
Build FlashInfer Docs #218: Commit 2e64a65 pushed by yzh119
July 3, 2024 18:09 57s main
July 3, 2024 18:09 57s
bump version: v0.0.8 (#355)
Build FlashInfer Docs #217: Commit 478447e pushed by yzh119
July 3, 2024 07:57 57s main
July 3, 2024 07:57 57s
ProTip! You can narrow down the results and go further in time using created:<2024-07-03 or the other filters available.