csrc/quantization/gptq_marlin/marlin_template.h · ce96857fdd2bf2390aaa2183561fd1a0f5c464c7 · OpenDAS / vllm_cscc · GitLab

"vllm/perf/benchmark_throughput.py" did not exist on "179285893c939c3841e211a7fd86719f54c60acb"

Find file Blame History Permalink

[Kernel][Quantization][MoE] add marlin kernel support for turing (sm75) (#29901) · ce96857f
Jinzhen Lin authored Dec 17, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
ce96857f

marlin_template.h 79.2 KB