Skip to content

Actions: flashinfer-ai/flashinfer

Actions

Build FlashInfer Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-doc.yml
572 workflow runs
572 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

bugfix: Fix the behavior of decode cuda graph wrapper (#291) Build FlashInfer Docs #166: Commit e252c94 pushed by yzh119
June 10, 2024 07:07 49s main
main
June 10, 2024 07:07 49s
bugfix: fix the synchronization issue in distributed operators (#290) Build FlashInfer Docs #165: Commit f13ec08 pushed by yzh119
June 9, 2024 08:49 1m 0s main
main
June 9, 2024 08:49 1m 0s
feat: initial support of distributed operators (#289) Build FlashInfer Docs #164: Commit 03553da pushed by yzh119
June 8, 2024 08:24 44s main
main
June 8, 2024 08:24 44s
cmake: fix DECODE_F8_DTYPES and DECODE_FP8_DTYPES discrepancy (#287) Build FlashInfer Docs #163: Commit 809abaa pushed by yzh119
June 7, 2024 08:13 48s main
main
June 7, 2024 08:13 48s
bugfix: fix the data type of aligned_alloc in handlers (#283) Build FlashInfer Docs #162: Commit 5a38066 pushed by yzh119
June 5, 2024 06:58 1m 1s main
main
June 5, 2024 06:58 1m 1s
feat: add group gemm operators (#282) Build FlashInfer Docs #161: Commit e08ba42 pushed by yzh119
June 5, 2024 03:28 49s main
main
June 5, 2024 03:28 49s
Add dtype checks for q-kv tensors (#280) Build FlashInfer Docs #160: Commit 7aadc0d pushed by yzh119
June 4, 2024 05:42 49s main
main
June 4, 2024 05:42 49s
bugfix: fix cudagraph-compatible prefill/decode apis (#281) Build FlashInfer Docs #159: Commit 1092e7e pushed by yzh119
June 4, 2024 05:21 55s main
main
June 4, 2024 05:21 55s
misc: suppress compilation warning of fastdiv (#279) Build FlashInfer Docs #158: Commit 7def34e pushed by yzh119
June 2, 2024 19:00 46s main
main
June 2, 2024 19:00 46s
perm: add fastdiv for uint32_t (#278) Build FlashInfer Docs #157: Commit ad1b202 pushed by yzh119
June 2, 2024 11:21 54s main
main
June 2, 2024 11:21 54s
feat: support cuda graph for batched multi-query(prefill/append) atte… Build FlashInfer Docs #156: Commit 24cc583 pushed by yzh119
June 2, 2024 09:14 42s main
main
June 2, 2024 09:14 42s
Revert "feat: support cuda graph for batched multi-query(prefill/appe… Build FlashInfer Docs #155: Commit 081a4c5 pushed by yzh119
June 2, 2024 09:11 44s main
main
June 2, 2024 09:11 44s
feat: support cuda graph for batched multi-query(prefill/append) atte… Build FlashInfer Docs #154: Commit 83ceb67 pushed by yzh119
June 2, 2024 09:08 56s main
main
June 2, 2024 09:08 56s
fp8: add calibration scale for decode attention operators (#273) Build FlashInfer Docs #153: Commit 041b63a pushed by yzh119
June 1, 2024 10:35 45s main
main
June 1, 2024 10:35 45s
hotfix: fix setup.py (#274) Build FlashInfer Docs #152: Commit 64e935a pushed by yzh119
June 1, 2024 06:53 56s main
main
June 1, 2024 06:53 56s
git: ignore generated directory in documentation (#272) Build FlashInfer Docs #151: Commit ab92880 pushed by yzh119
May 30, 2024 21:11 43s main
main
May 30, 2024 21:11 43s
doc: add some documentation for attention with mask API (#271) Build FlashInfer Docs #150: Commit 48941fa pushed by yzh119
May 30, 2024 01:08 50s main
main
May 30, 2024 01:08 50s
doc: update documentation for mask layout (#270) Build FlashInfer Docs #149: Commit c6b7c20 pushed by yzh119
May 28, 2024 08:39 51s main
main
May 28, 2024 08:39 51s
3rdparty: add dependency to cutlass and composable kernels (#269) Build FlashInfer Docs #148: Commit b16bbe4 pushed by yzh119
May 28, 2024 07:11 1m 4s main
main
May 28, 2024 07:11 1m 4s
3rdparty: add mscclpp dependency (#268) Build FlashInfer Docs #147: Commit 2bdacfe pushed by yzh119
May 28, 2024 06:45 39s main
main
May 28, 2024 06:45 39s
bugfix: avoid potential illegal memory access (#267) Build FlashInfer Docs #146: Commit 79a2125 pushed by yzh119
May 28, 2024 06:40 43s main
main
May 28, 2024 06:40 43s
feat: support custom attention mask in prefill/append attention kerne… Build FlashInfer Docs #145: Commit 7304282 pushed by yzh119
May 28, 2024 06:24 40s main
main
May 28, 2024 06:24 40s
bugfix: use FlagHeads instead of SubtractLeft for cuda 118 (#265) Build FlashInfer Docs #144: Commit 08ab1c1 pushed by yzh119
May 27, 2024 22:44 44s main
main
May 27, 2024 22:44 44s
doc: bugfix in kv-layout docs (#264) Build FlashInfer Docs #143: Commit 316b2e1 pushed by yzh119
May 27, 2024 20:36 38s main
main
May 27, 2024 20:36 38s
doc: update documentation (#263) Build FlashInfer Docs #142: Commit 2814233 pushed by yzh119
May 27, 2024 17:28 42s main
main
May 27, 2024 17:28 42s
ProTip! You can narrow down the results and go further in time using created:<2024-05-27 or the other filters available.