Skip to content

Actions: neuralmagic/AutoFP8

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
62 workflow runs
62 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update README.md test #68: Commit e944610 pushed by mgoin
October 1, 2024 19:38 2m 40s main
main
October 1, 2024 19:38 2m 40s
Separate kv_scale into k_scale and v_scale (#25) test #65: Commit 2cd265f pushed by mgoin
July 23, 2024 16:26 3m 1s main
main
July 23, 2024 16:26 3m 1s
Switch backend to use llm-compressor test #64: Pull request #33 synchronize by mgoin
July 19, 2024 14:30 2m 30s use-llm-compressor
use-llm-compressor
July 19, 2024 14:30 2m 30s
Switch backend to use llm-compressor test #63: Pull request #33 synchronize by mgoin
July 18, 2024 21:57 2m 40s use-llm-compressor
use-llm-compressor
July 18, 2024 21:57 2m 40s
Switch backend to use llm-compressor test #62: Pull request #33 synchronize by mgoin
July 18, 2024 21:54 2m 45s use-llm-compressor
use-llm-compressor
July 18, 2024 21:54 2m 45s
Switch backend to use llm-compressor test #61: Pull request #33 synchronize by mgoin
July 18, 2024 21:41 2m 44s use-llm-compressor
use-llm-compressor
July 18, 2024 21:41 2m 44s
Switch backend to use llm-compressor test #60: Pull request #33 synchronize by mgoin
July 18, 2024 21:40 20s use-llm-compressor
use-llm-compressor
July 18, 2024 21:40 20s
Switch backend to use llm-compressor test #59: Pull request #33 synchronize by mgoin
July 18, 2024 21:38 20s use-llm-compressor
use-llm-compressor
July 18, 2024 21:38 20s
Switch backend to use llm-compressor test #58: Pull request #33 synchronize by mgoin
July 18, 2024 21:36 2m 14s use-llm-compressor
use-llm-compressor
July 18, 2024 21:36 2m 14s
Switch backend to use llm-compressor test #57: Pull request #33 synchronize by mgoin
July 18, 2024 21:12 2m 11s use-llm-compressor
use-llm-compressor
July 18, 2024 21:12 2m 11s
Switch backend to use llm-compressor test #56: Pull request #33 synchronize by mgoin
July 18, 2024 21:11 2m 9s use-llm-compressor
use-llm-compressor
July 18, 2024 21:11 2m 9s
Switch backend to use llm-compressor test #55: Pull request #33 synchronize by mgoin
July 18, 2024 21:10 2m 8s use-llm-compressor
use-llm-compressor
July 18, 2024 21:10 2m 8s
Separate kv_scale into k_scale and v_scale test #54: Pull request #25 synchronize by mgoin
July 16, 2024 19:15 4m 16s separate-key-value-scale
separate-key-value-scale
July 16, 2024 19:15 4m 16s
Separate kv_scale into k_scale and v_scale test #53: Pull request #25 opened by mgoin
July 3, 2024 00:49 2m 32s separate-key-value-scale
separate-key-value-scale
July 3, 2024 00:49 2m 32s
Update example_dataset.py test #52: Commit 4b2092c pushed by mgoin
July 1, 2024 15:35 5m 30s main
main
July 1, 2024 15:35 5m 30s
Update example_mixtral.py test #51: Commit 1958d07 pushed by mgoin
June 27, 2024 18:48 2m 58s main
main
June 27, 2024 18:48 2m 58s
Add automatic batching test #50: Pull request #22 opened by mgoin
June 19, 2024 15:50 2m 43s auto-batch
auto-batch
June 19, 2024 15:50 2m 43s
Update README.md (#21) test #49: Commit 2a9330c pushed by mgoin
June 19, 2024 15:00 4m 11s main
main
June 19, 2024 15:00 4m 11s
Update README.md test #48: Pull request #21 opened by mgoin
June 19, 2024 13:38 2m 45s mgoin-patch-1
mgoin-patch-1
June 19, 2024 13:38 2m 45s
Support calibrating kv cache scales (#17) test #47: Commit 0d40b99 pushed by mgoin
June 18, 2024 22:53 2m 41s main
main
June 18, 2024 22:53 2m 41s
Support calibrating kv cache scales test #46: Pull request #17 synchronize by mgoin
June 18, 2024 17:25 8m 28s support-kv-cache-scales
support-kv-cache-scales
June 18, 2024 17:25 8m 28s
Support calibrating kv cache scales test #45: Pull request #17 synchronize by mgoin
June 18, 2024 16:12 2m 48s support-kv-cache-scales
support-kv-cache-scales
June 18, 2024 16:12 2m 48s
Support calibrating kv cache scales test #44: Pull request #17 synchronize by mgoin
June 17, 2024 17:45 2m 40s support-kv-cache-scales
support-kv-cache-scales
June 17, 2024 17:45 2m 40s
Use torch.inference_mode() for lower memory usage during calibratio… test #43: Commit b1c6ad6 pushed by mgoin
June 17, 2024 16:40 2m 23s main
main
June 17, 2024 16:40 2m 23s
Use torch.inference_mode() for lower memory usage during calibration test #42: Pull request #20 opened by mgoin
June 17, 2024 16:31 4m 15s torch-inference-mode
torch-inference-mode
June 17, 2024 16:31 4m 15s