Skip to content

Actions: flashinfer-ai/flashinfer

Actions

Build FlashInfer Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ci: select 2_28 manylinux builder for new torch+cuda versions (#1000) Build FlashInfer Docs #644: Commit 382a4d7 pushed by yzh119
April 4, 2025 07:36 54s main
main
April 4, 2025 07:36 54s
release: bump version to v0.2.5 (#999) Build FlashInfer Docs #643: Commit 592b110 pushed by yzh119
April 4, 2025 00:39 53s main
main
April 4, 2025 00:39 53s
perf: add -DNDEBUG compilation flag (#998) Build FlashInfer Docs #642: Commit 9956c29 pushed by yzh119
April 4, 2025 00:36 45s main
main
April 4, 2025 00:36 45s
3rdparty: upgrade cutlass to 3.9 (#997) Build FlashInfer Docs #641: Commit 25d67b5 pushed by zhyncs
April 3, 2025 21:34 53s main
main
April 3, 2025 21:34 53s
feat: SM-constraint-GEMM by triton persistent kernel (#982) Build FlashInfer Docs #640: Commit 5751fc6 pushed by yzh119
April 1, 2025 19:36 50s main
main
April 1, 2025 19:36 50s
perf: prefetch page indices for mla kernel (#991) Build FlashInfer Docs #639: Commit d7a9234 pushed by yzh119
March 31, 2025 21:27 59s main
main
March 31, 2025 21:27 59s
misc: fix devcontainer conda path (#989) Build FlashInfer Docs #638: Commit 17ff5a7 pushed by yzh119
March 31, 2025 15:35 49s main
main
March 31, 2025 15:35 49s
ci: add torch 2.6+cu126 wheel (#985) Build FlashInfer Docs #637: Commit 72f00bc pushed by MasterJH5574
March 31, 2025 09:14 1m 7s main
main
March 31, 2025 09:14 1m 7s
misc: update devcontainer (#986) Build FlashInfer Docs #636: Commit 31cfe10 pushed by yzh119
March 30, 2025 21:24 1m 28s main
main
March 30, 2025 21:24 1m 28s
ci: switch to on-demand instances if spot instance is interrupted (#987) Build FlashInfer Docs #635: Commit afa9332 pushed by yzh119
March 30, 2025 20:55 51s main
main
March 30, 2025 20:55 51s
misc: Rename output_emitted_token_num -> `output_emitted_draft_toke… Build FlashInfer Docs #634: Commit 86da6b8 pushed by yzh119
March 29, 2025 21:13 49s main
main
March 29, 2025 21:13 49s
feat: Allow passing workspace base directory via environment variable… Build FlashInfer Docs #633: Commit bb028cc pushed by yzh119
March 29, 2025 19:03 48s main
main
March 29, 2025 19:03 48s
triton: Triton rms_norm kernels (#983) Build FlashInfer Docs #632: Commit 893172c pushed by yzh119
March 29, 2025 18:01 47s main
main
March 29, 2025 18:01 47s
misc: Use environment variable to control JIT verbose flag (#981) Build FlashInfer Docs #631: Commit 77ccda8 pushed by yzh119
March 29, 2025 17:59 44s main
main
March 29, 2025 17:59 44s
bugfix: Fix compilation with FP16_QK_REDUCTION enabled. (#962) Build FlashInfer Docs #630: Commit 3a69560 pushed by yzh119
March 29, 2025 06:28 55s main
main
March 29, 2025 06:28 55s
release: bump version to v0.2.4 (#980) Build FlashInfer Docs #629: Commit bc81a59 pushed by yzh119
March 29, 2025 05:08 51s main
main
March 29, 2025 05:08 51s
perf: Use 2WG pipeline design for MLA implementation on Hopper (#952) Build FlashInfer Docs #628: Commit 60d37b7 pushed by yzh119
March 29, 2025 04:34 49s main
main
March 29, 2025 04:34 49s
perf: dual pivot top-p/top-k renorm (#974) Build FlashInfer Docs #627: Commit e19cb7b pushed by yzh119
March 27, 2025 09:04 47s main
main
March 27, 2025 09:04 47s
benchmark: add sampling.renorm benchmarks (#970) Build FlashInfer Docs #626: Commit 588c2fb pushed by yzh119
March 25, 2025 21:15 50s main
main
March 25, 2025 21:15 50s
bugfix: Fix POD JIT bugs (#971) Build FlashInfer Docs #625: Commit 55a6668 pushed by yzh119
March 25, 2025 03:16 55s main
main
March 25, 2025 03:16 55s
perf: Fix python API overhead when CUDAGraph is not enabled (#969) Build FlashInfer Docs #624: Commit 61e049a pushed by yzh119
March 24, 2025 04:19 53s main
main
March 24, 2025 04:19 53s
feat: Added tvm binding for sampling kernel (#958) Build FlashInfer Docs #623: Commit f65b93f pushed by yzh119
March 24, 2025 02:47 46s main
main
March 24, 2025 02:47 46s
perf: reduce torch.library dispatch overhead (#968) Build FlashInfer Docs #622: Commit 86b12ad pushed by yzh119
March 22, 2025 09:16 1m 11s main
main
March 22, 2025 09:16 1m 11s
doc: remove misleading docstring about non_blocking (#966) Build FlashInfer Docs #621: Commit bb49fac pushed by yzh119
March 22, 2025 08:24 57s main
main
March 22, 2025 08:24 57s
bugfix: Fix compilation on cuda 12.2 (#961) Build FlashInfer Docs #620: Commit 034fc18 pushed by yzh119
March 19, 2025 16:57 53s main
main
March 19, 2025 16:57 53s