Skip to content
CI Pipeline

perf: +8-9% on Qwen3.5-122B-A10B SSD-stream via stacked-buffer + Gate+Up fusion in mlx-swift-lm #298

Sign in to view logs

perf: +8-9% on Qwen3.5-122B-A10B SSD-stream via stacked-buffer + Gate+Up fusion in mlx-swift-lm

perf: +8-9% on Qwen3.5-122B-A10B SSD-stream via stacked-buffer + Gate+Up fusion in mlx-swift-lm #298

Run time

Learn about OS pricing on GitHub Actions
Job Run time
build_and_unit_test
11m 2s
dflash-speculative-decoding
11m 7s
speculative-decoding
11m 57s
speculative-decoding-eval
8m 44s
ssd-draft-memory-guard
1m 13s
integration_matrix (graph)
37s
integration_matrix (server)
1m 15s
integration_matrix (omni)
1m 58s
integration_matrix (vision)
1m 3s
integration_matrix (opencode)
4m 12s
integration_matrix (audio)
3m 14s
56m 22s