Skip to content

perf: add low-latency nz quantized decode matmul. - #42

Open
maojunx99 wants to merge 3 commits into
xLLM-AI:mainfrom
maojunx99:perf/qwen3vl-decode-nofusion
Open

perf: add low-latency nz quantized decode matmul.#42
maojunx99 wants to merge 3 commits into
xLLM-AI:mainfrom
maojunx99:perf/qwen3vl-decode-nofusion

perf: specialize decode matmul shapes

74686ce
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs