Skip to content

Actions: flashinfer-ai/flashinfer

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,148 workflow runs
1,148 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat: Naive Support for Hopper FP8 Prefill Kernel with Per-Head Quant…
Build FlashInfer Docs #587: Commit f5dec3d pushed by yzh119
February 27, 2025 21:30 48s main
February 27, 2025 21:30 48s
Release
Release #112: Manually run by zhyncs
February 27, 2025 16:29 1h 6m 12s main
February 27, 2025 16:29 1h 6m 12s
Release Wheel
Release Wheel #13: Manually run by zhyncs
February 27, 2025 16:29 36m 25s main
February 27, 2025 16:29 36m 25s
release: bump version v0.2.2.post1 (#902)
Build FlashInfer Docs #586: Commit 1dba037 pushed by yzh119
February 27, 2025 05:59 50s main
February 27, 2025 05:59 50s
perf: tweak the pipeline design of mla kernel (#901)
Build FlashInfer Docs #585: Commit 0ed1ce8 pushed by yzh119
February 27, 2025 05:55 56s main
February 27, 2025 05:55 56s
perf: use f16 as split-k partial output data type (#900)
Build FlashInfer Docs #584: Commit e4a68e4 pushed by yzh119
February 27, 2025 04:00 49s main
February 27, 2025 04:00 49s
perf: fix MLA split-k performance bug (#898)
Build FlashInfer Docs #583: Commit 1e330b7 pushed by yzh119
February 26, 2025 01:32 58s main
February 26, 2025 01:32 58s
Release
Release #111: Manually run by zhyncs
February 25, 2025 17:52 1h 6m 51s bump-version-0.2.2
February 25, 2025 17:52 1h 6m 51s
perf: tweak register amount for producer/consumer in MLA template (#896)
Build FlashInfer Docs #582: Commit 56e56ea pushed by yzh119
February 24, 2025 17:41 48s main
February 24, 2025 17:41 48s
fix: pin_memory use cpu as default device (#895)
Build FlashInfer Docs #581: Commit 22f3c87 pushed by yzh119
February 24, 2025 15:57 1m 4s main
February 24, 2025 15:57 1m 4s
perf: fix the performance of stage stage of split-k (#894)
Build FlashInfer Docs #580: Commit 341ae09 pushed by yzh119
February 24, 2025 08:01 58s main
February 24, 2025 08:01 58s
Release Wheel
Release Wheel #12: Manually run by zhyncs
February 24, 2025 01:59 28m 25s main
February 24, 2025 01:59 28m 25s
release: bump version to v0.2.2 (#891)
Build FlashInfer Docs #579: Commit 28053ac pushed by yzh119
February 23, 2025 22:28 45s main
February 23, 2025 22:28 45s
unittest: add unittests for MLA + cudagraph (#890)
Build FlashInfer Docs #578: Commit 977d3fe pushed by yzh119
February 23, 2025 20:35 52s main
February 23, 2025 20:35 52s
typo: Fixing several typos in doc file kv_layout.rst (#884)
Build FlashInfer Docs #577: Commit dc18f66 pushed by yzh119
February 23, 2025 19:57 46s main
February 23, 2025 19:57 46s
[JIT] Fix MLA header in TVM binding (#889)
Build FlashInfer Docs #576: Commit ce34c1f pushed by yzh119
February 23, 2025 19:08 47s main
February 23, 2025 19:08 47s
perf: FlashAttention-3 style MLA PageAttention (#887)
Build FlashInfer Docs #575: Commit 2b24293 pushed by yzh119
February 23, 2025 11:37 47s main
February 23, 2025 11:37 47s
[Hotfix] Add flashinfer.jit.attention into packages (#881)
Build FlashInfer Docs #574: Commit 26c0296 pushed by yzh119
February 20, 2025 05:51 50s main
February 20, 2025 05:51 50s
jit: JIT compilation support for TVM (#880)
Build FlashInfer Docs #573: Commit df05064 pushed by yzh119
February 19, 2025 20:32 47s main
February 19, 2025 20:32 47s
misc:Remove unused k_smem_offset_w update in MLA kernel (#878)
Build FlashInfer Docs #572: Commit 1605eaa pushed by yzh119
February 19, 2025 18:13 58s main
February 19, 2025 18:13 58s
[API] Fix top_k_top_p_sampling_from_logits param typo (#875)
Build FlashInfer Docs #571: Commit 68a0378 pushed by yzh119
February 18, 2025 22:55 56s main
February 18, 2025 22:55 56s
bugfix: fix geneate_dispatch_inc args from parser (#870)
Build FlashInfer Docs #570: Commit 78dde79 pushed by yzh119
February 18, 2025 16:19 47s main
February 18, 2025 16:19 47s
add lightllm adoption (#871)
Build FlashInfer Docs #569: Commit 7e06dc0 pushed by zhyncs
February 18, 2025 08:38 54s main
February 18, 2025 08:38 54s
typo: fix a bunch of typos. (#862)
Build FlashInfer Docs #568: Commit fbb3135 pushed by yzh119
February 18, 2025 02:11 53s main
February 18, 2025 02:11 53s
bugfix: fix the behavior of MLA kernel when kv-length is 0 (#868)
Build FlashInfer Docs #567: Commit 6ec3bae pushed by yzh119
February 17, 2025 21:56 57s main
February 17, 2025 21:56 57s