Skip to content
MLX

[cuda backend] reduce memory consumption on gemma4_31b by running embedding in int8 #1723

Sign in to view logs

[cuda backend] reduce memory consumption on gemma4_31b by running embedding in int8

[cuda backend] reduce memory consumption on gemma4_31b by running embedding in int8 #1723

Run time

Learn about OS pricing on GitHub Actions
Job Run time
CI run decision / decide
30s
test-mlx-voxtral-realtime / test-mlx-voxtral-realtime
40m 17s
test-mlx-parakeet / test-mlx-parakeet
34m 6s
test-mlx-whisper / test-mlx-whisper
9m 47s
test-mlx-qwen35-moe / test-mlx-qwen35-moe
9m 51s
test-mlx-stories110m / test-mlx-stories110m
36m 46s
test-mlx / test-mlx
13m 49s
test-mlx-voxtral / test-mlx-voxtral
41m 20s
backend-tester (operators) / test-mlx-backend-operators
11m 29s
backend-tester (models) / test-mlx-backend-models
12m 20s
test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, false, 4w, macos-14-xlarge) / test-mlx-llm-llama-1b-4w
10m 59s
test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, true, 4w, macos-14-xlarge) / test-mlx-llm-llama-1b-custom-4w
11m 5s
test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-gemma3-1b-custom-nvfp4
10m 58s
test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, true, 4w, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-custom-4w
10m 22s
test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, true, 4w, macos-14-xlarge) / test-mlx-llm-gemma3-1b-custom-4w
10m 50s
test-mlx-llm (google/gemma-4-E2B-it, gemma4-e2b, true, 4w, macos-15-xlarge) / test-mlx-llm-gemma4-e2b-custom-4w
18m 0s
test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-custom-nvfp4
10m 45s
test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-llama-1b-nvfp4
10m 29s
test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-llama-1b-custom-nvfp4
11m 18s
test-mlx-llm (google/gemma-4-E2B-it, gemma4-e2b, false, 4w, macos-15-xlarge) / test-mlx-llm-gemma4-e2b-4w
18m 0s
test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, false, 4w, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-4w
10m 35s
test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-gemma3-1b-nvfp4
11m 1s
test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-nvfp4
10m 19s
test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, false, 4w, macos-14-xlarge) / test-mlx-llm-gemma3-1b-4w
11m 42s
6h 16m 38s