Repository

Gxj230958/TritonAscendBench

A migration benchmark that measures whether production GPU Triton kernels — extracted from vLLM and SGLang inference paths — can be ported to the Huawei Ascend 910B (Atlas A2) via `triton-ascend` without losing correctness or performance.

Open source AI & agents PythonApache-2.0

Stars

145

Today

+9

last 24 hours

This week

+9

Forks

0

Clone

git clone https://github.com/Gxj230958/TritonAscendBench.git

Star growth

2026-10-18: +9 (today so far)2026-10-18todaymax +9/day
Stars gained per day. Tracking since 2026-10-18; the lighter bar is today so far.
Created
2026-09-16
Last commit
2026-10-15
Gained since tracking
+9

Updated Sun, 18 Oct 2026 15:32:30 GMT · description from the project itself