flashinfer-ai/flashinfer
View on GitHubFlashInfer: Kernel Library for LLM Serving
- Stars
- 6.4k
- Forks
- 1.5k
- Open beginner issues
- 0
- Indexed issues
- 322
- Avg merge
- 4d 13h
- Merged PRs (30d)
- 273
- Dominant language
- Cuda
- License
- Apache-2.0
- Last GitHub push
- Sep 17, 2026
- Latest indexed
- Sep 16, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- good first issue
-
feature request op: attention performance
flashinfer-ai/flashinfer#565 · 4 comments · 0 reactions · 0 assignees ·
-
bug op: attention
flashinfer-ai/flashinfer#730 · 2 comments · 0 reactions · 0 assignees ·
-
feature request op: attention
flashinfer-ai/flashinfer#742 · 1 comment · 3 reactions · 0 assignees ·
-
op: misc priority: should have (P1) vllm
flashinfer-ai/flashinfer#1104 · 12 comments · 3 reactions · 1 assignee ·
-
op: attention question
flashinfer-ai/flashinfer#1185 · 1 comment · 0 reactions · 0 assignees ·
-
bug op: attention performance
flashinfer-ai/flashinfer#1353 · 5 comments · 2 reactions · 1 assignee ·
-
op: attention performance
flashinfer-ai/flashinfer#1474 · 3 comments · 0 reactions · 0 assignees ·
-
op: attention priority: should have (P1) v0.4.0
flashinfer-ai/flashinfer#1606 · 3 comments · 0 reactions · 1 assignee ·
-
bug numerical issue op: moe
flashinfer-ai/flashinfer#1646 · 3 comments · 0 reactions · 0 assignees ·
-
feature request op: attention priority: should have (P1)
flashinfer-ai/flashinfer#1654 · 3 comments · 1 reaction · 1 assignee ·
-
op: moe priority: should have (P1)
flashinfer-ai/flashinfer#1669 · 2 comments · 0 reactions · 0 assignees ·
-
Error on H800 Openbug op: attention
flashinfer-ai/flashinfer#1671 · 6 comments · 0 reactions · 1 assignee ·
-
jit priority: should have (P1) refactor
flashinfer-ai/flashinfer#1751 · 2 comments · 2 reactions · 0 assignees ·
-
op: attention performance question
flashinfer-ai/flashinfer#1753 · 8 comments · 0 reactions · 0 assignees ·
-
feature request op: gemm
flashinfer-ai/flashinfer#1762 · 0 comments · 1 reaction · 0 assignees ·
-
flashinfer-ai/flashinfer#1936 · 0 comments · 0 reactions · 0 assignees ·
-
feature request priority: nice to have (P2)
flashinfer-ai/flashinfer#1941 · 3 comments · 0 reactions · 0 assignees ·
-
feature request priority: should have (P1)
flashinfer-ai/flashinfer#2004 · 2 comments · 0 reactions · 0 assignees ·
-
op: attention performance priority: nice to have (P2)
flashinfer-ai/flashinfer#2066 · 3 comments · 0 reactions · 1 assignee ·
-
feature request op: attention priority: nice to have (P2) trtllm
flashinfer-ai/flashinfer#2107 · 5 comments · 0 reactions · 1 assignee ·
-
bug op: attention
flashinfer-ai/flashinfer#2150 · 1 comment · 0 reactions · 1 assignee ·
-
bug op: attention
flashinfer-ai/flashinfer#2207 · 0 comments · 0 reactions · 0 assignees ·
-
bug op: attention
flashinfer-ai/flashinfer#2208 · 3 comments · 0 reactions · 1 assignee ·
-
feature request priority: should have (P1) testing
flashinfer-ai/flashinfer#2225 · 0 comments · 0 reactions · 0 assignees ·
-
feature request op: gemm priority: should have (P1)
flashinfer-ai/flashinfer#2290 · 10 comments · 0 reactions · 0 assignees ·
-
feature request op: attention priority: should have (P1)
flashinfer-ai/flashinfer#2292 · 2 comments · 0 reactions · 0 assignees ·
-
feature request
flashinfer-ai/flashinfer#2317 · 2 comments · 0 reactions · 1 assignee ·
-
cute-dsl good first issue op: comm op: gemm refactor
flashinfer-ai/flashinfer#2359 · 10 comments · 0 reactions · 1 assignee ·
-
op: comm priority: must have (P0) vllm
flashinfer-ai/flashinfer#2364 · 5 comments · 6 reactions · 1 assignee ·
-
documentation question
flashinfer-ai/flashinfer#2406 · 2 comments · 2 reactions · 0 assignees ·
-
model: dsr1 op: comm question
flashinfer-ai/flashinfer#2407 · 5 comments · 0 reactions · 1 assignee ·
-
feature request op: attention performance priority: should have (P1) trtllm
flashinfer-ai/flashinfer#2408 · 6 comments · 0 reactions · 0 assignees ·
-
feature request op: attention
flashinfer-ai/flashinfer#2424 · 2 comments · 0 reactions · 1 assignee ·
-
model: flux model: wan op: gemm priority: must have (P0)
flashinfer-ai/flashinfer#2430 · 0 comments · 0 reactions · 1 assignee ·
-
op: comm priority: must have (P0) vllm
flashinfer-ai/flashinfer#2434 · 3 comments · 0 reactions · 1 assignee ·
-
op: comm op: gemm priority: must have (P0) vllm
flashinfer-ai/flashinfer#2435 · 5 comments · 0 reactions · 1 assignee ·
-
op: misc
flashinfer-ai/flashinfer#2491 · 4 comments · 0 reactions · 1 assignee ·
-
bug op: gemm
flashinfer-ai/flashinfer#2514 · 1 comment · 0 reactions · 1 assignee ·
-
feature request op: attention
flashinfer-ai/flashinfer#2522 · 1 comment · 0 reactions · 0 assignees ·
-
model: qwen3.5 / 3.6 / 3.8 op: moe
flashinfer-ai/flashinfer#2595 · 5 comments · 1 reaction · 1 assignee ·
-
needs-triage
flashinfer-ai/flashinfer#2597 · 0 comments · 0 reactions · 0 assignees ·
-
cute-dsl op: gemm priority: should have (P1)
flashinfer-ai/flashinfer#2621 · 5 comments · 0 reactions · 1 assignee ·
-
op: attention
flashinfer-ai/flashinfer#2632 · 3 comments · 0 reactions · 0 assignees ·
-
priority: should have (P1) wip
flashinfer-ai/flashinfer#2649 · 1 comment · 0 reactions · 1 assignee ·
-
op: moe op: moe-routing
flashinfer-ai/flashinfer#2671 · 4 comments · 0 reactions · 1 assignee ·
-
model: qwen3.5 / 3.6 / 3.8 op: attention op: linear attention priority: must have (P0)
flashinfer-ai/flashinfer#2687 · 52 comments · 3 reactions · 2 assignees ·
-
op: misc
flashinfer-ai/flashinfer#2733 · 0 comments · 0 reactions · 0 assignees ·
-
model: dsr1 model: kimi-k2.5 needs-triage priority: should have (P1)
flashinfer-ai/flashinfer#2745 · 8 comments · 0 reactions · 0 assignees ·
-
needs-triage
flashinfer-ai/flashinfer#2765 · 2 comments · 0 reactions · 1 assignee ·
-
needs-triage op: attention priority: should have (P1)
flashinfer-ai/flashinfer#2766 · 3 comments · 0 reactions · 1 assignee ·