You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -28,7 +28,7 @@ The core features of FlashInfer include:
28
28
5.**CUDAGraph and torch.compile Compatibility**: FlashInfer kernels can be captured by CUDAGraphs and torch.compile for low-latency inference.
29
29
6.**Efficient LLM-specific Operators**: High-Performance [fused kernel for Top-P, Top-K/Min-P sampling](https://docs.flashinfer.ai/api/sampling.html) without the need to sorting.
30
30
31
-
FlashInfer support PyTorch, TVM and C++ (header-only) APIs, and can be easily integrated into existing projects.
31
+
FlashInfer supports PyTorch, TVM and C++ (header-only) APIs, and can be easily integrated into existing projects.
32
32
33
33
## News
34
34
-[Dec 16, 2024][Blog Post](https://flashinfer.ai/2024/12/16/flashinfer-v02-release.html) FlashInfer 0.2 - Efficient and Customizable Kernels for LLM Inference Serving
0 commit comments