Skip to content

Actions: flashinfer-ai/flashinfer

Actions

Build FlashInfer Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-doc.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[feat] Trtllm-gen Per-token Nvfp4 MoE Build FlashInfer Docs #5543: Pull request #3027 synchronize by IwakuraRein
2m 6s IwakuraRein:per-token-fp4
IwakuraRein:per-token-fp4
2m 6s
[feat] Trtllm-gen Per-token Nvfp4 MoE Build FlashInfer Docs #5542: Pull request #3027 synchronize by IwakuraRein
2m 3s IwakuraRein:per-token-fp4
IwakuraRein:per-token-fp4
2m 3s
[feat] Trtllm-gen Per-token Nvfp4 MoE Build FlashInfer Docs #5541: Pull request #3027 synchronize by IwakuraRein
3m 35s IwakuraRein:per-token-fp4
IwakuraRein:per-token-fp4
3m 35s
Add device-side NaN check instrumentation for MXFP8 pipeline debugging Build FlashInfer Docs #5540: Pull request #3035 opened by kahyunnam
2m 15s nan-check-instrumentation
nan-check-instrumentation
2m 15s
trtllm fmha oss kernels Build FlashInfer Docs #5539: Pull request #3034 opened by saltyminty
2m 24s fix/mingyangw/trtllm_fmha_kernels
fix/mingyangw/trtllm_fmha_kernels
2m 24s
Prevent MoE autotuner buffer overflow on large token buckets (#3025) Build FlashInfer Docs #5538: Commit a1166dc pushed by nv-yunzheq
2m 11s main
main
2m 11s
[feat] Trtllm-gen Per-token Nvfp4 MoE Build FlashInfer Docs #5537: Pull request #3027 synchronize by IwakuraRein
2m 15s IwakuraRein:per-token-fp4
IwakuraRein:per-token-fp4
2m 15s
trtllm non causal support Build FlashInfer Docs #5536: Pull request #3020 synchronize by saltyminty
1m 57s fix/mingyangw/2826-trtllm-gen-non-causal-support
fix/mingyangw/2826-trtllm-gen-non-causal-support
1m 57s
[fix] bugfix 541: Make single_prefill/decode compatible with torch.co… Build FlashInfer Docs #5535: Commit 9dc802c pushed by yzh119
2m 16s main
main
2m 16s
Prevent MoE autotuner buffer overflow on large token buckets Build FlashInfer Docs #5534: Pull request #3025 synchronize by nv-yunzheq
2m 10s leejnau:cutedsl-moe-autotuner-buffer-overflow
leejnau:cutedsl-moe-autotuner-buffer-overflow
2m 10s
trtllm non causal support Build FlashInfer Docs #5533: Pull request #3020 synchronize by saltyminty
2m 11s fix/mingyangw/2826-trtllm-gen-non-causal-support
fix/mingyangw/2826-trtllm-gen-non-causal-support
2m 11s
fused_moe: pre-filter SM89 tactics with zero occupancy on SM120 Blackwell (fix review feedback on #2764) Build FlashInfer Docs #5532: Pull request #3032 synchronize by aniskumar-nv
Action required aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
Action required
fused_moe: pre-filter SM89 tactics with zero occupancy on SM120 Blackwell (fix review feedback on #2764) Build FlashInfer Docs #5531: Pull request #3032 synchronize by aniskumar-nv
Action required aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
Action required
perf: Optimize CUTLASS MoE helper kernels for small-batch decode work… Build FlashInfer Docs #5530: Commit 6248936 pushed by aleozlx
3m 19s main
main
3m 19s
perf: Port TRT-LLM SM120/SM121 FP4 CUTLASS GEMM optimizations. Add PD… Build FlashInfer Docs #5529: Commit c0adda7 pushed by bkryu
2m 16s main
main
2m 16s
fused_moe: pre-filter SM89 tactics with zero occupancy on SM120 Blackwell (fix review feedback on #2764) Build FlashInfer Docs #5528: Pull request #3032 opened by aniskumar-nv
Action required aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
aniskumar-nv:fix/fused-moe-sm89-tactics-on-sm120
Action required
[CuTe DSL] Add modular FMHA prefill and MLA decode attention kernels Build FlashInfer Docs #5527: Pull request #2805 synchronize by pgera
2m 0s pgera:cutedsl-fmha-prefill
pgera:cutedsl-fmha-prefill
2m 0s
fix: check for ptr before calling close_mnnvl_memory Build FlashInfer Docs #5526: Pull request #2892 synchronize by jdebache
2m 13s jdebache:handle_mnnvl_memory_open_failure
jdebache:handle_mnnvl_memory_open_failure
2m 13s
fix: broadcast input_global_scale [1] to [num_experts] in scaled_fp4_grouped_quantize Build FlashInfer Docs #5525: Pull request #2977 synchronize by namgyu-youn
Action required namgyu-youn:fix-scaled-fp4-quantize
namgyu-youn:fix-scaled-fp4-quantize
Action required
feat: preparing TRTLLM MoE backend to support more kernels Build FlashInfer Docs #5524: Pull request #2794 synchronize by rosenrodt
2m 18s rosenrodt:feat/prepare-trtllm-moe-tput-support-2
rosenrodt:feat/prepare-trtllm-moe-tput-support-2
2m 18s
[feat] Add blackwell GDN prefill kernel Build FlashInfer Docs #5523: Pull request #3001 synchronize by jiahanc
2m 47s jiahanc:BlackwellGDN
jiahanc:BlackwellGDN
2m 47s
Update Docker CI tags to 20260408-4cce866 (#3018) Build FlashInfer Docs #5522: Commit 074e163 pushed by yzh119
2m 16s main
main
2m 16s
Update Docker CI tags to 20260408-4cce866 Build FlashInfer Docs #5521: Pull request #3018 synchronize by bkryu
2m 55s update-docker-tags-20260408-4cce866
update-docker-tags-20260408-4cce866
2m 55s
Fix autotuner crash and add autotuning tests for routed MoE Build FlashInfer Docs #5520: Pull request #3028 synchronize by wzhao18
2m 12s wzhao18:wzhao/fix-autotuner-crash
wzhao18:wzhao/fix-autotuner-crash
2m 12s
Fix autotuner crash and add autotuning tests for routed MoE Build FlashInfer Docs #5519: Pull request #3028 opened by wzhao18
2m 11s wzhao18:wzhao/fix-autotuner-crash
wzhao18:wzhao/fix-autotuner-crash
2m 11s