Skip to content

Actions: casper-hansen/AutoAWQ

Actions

Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docs.yaml
106 workflow runs
106 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update generate example to llama 3 (#448) Documentation #31: Commit edcf780 pushed by casper-hansen
April 18, 2024 17:09 25s main
main
April 18, 2024 17:09 25s
Fix starcoder2 fused norm (#442) Documentation #30: Commit 0e52a5c pushed by casper-hansen
April 12, 2024 16:46 25s main
main
April 12, 2024 16:46 25s
Add StableLM support (#410) Documentation #29: Commit e9f6269 pushed by casper-hansen
April 6, 2024 13:15 32s main
main
April 6, 2024 13:15 32s
add starcoder2 support (#406) Documentation #28: Commit 33dfb04 pushed by casper-hansen
April 6, 2024 13:06 28s main
main
April 6, 2024 13:06 28s
Add download_kwargs for load model (#302) (#399) Documentation #27: Commit eb85f67 pushed by casper-hansen
April 6, 2024 12:41 27s main
main
April 6, 2024 12:41 27s
Workaround: illegal memory access (#421) Documentation #26: Commit f835379 pushed by casper-hansen
April 6, 2024 12:37 28s main
main
April 6, 2024 12:37 28s
Implement apply_clip argument to quantize() (#427) Documentation #25: Commit b5db7fc pushed by casper-hansen
April 6, 2024 12:36 24s main
main
April 6, 2024 12:36 24s
Pin: lm_eval==0.4.1 (#426) Documentation #24: Commit c780d65 pushed by casper-hansen
April 6, 2024 12:15 31s main
main
April 6, 2024 12:15 31s
FIX: Add safe guards for static cache + llama on transformers latest … Documentation #23: Commit 1f07200 pushed by casper-hansen
April 6, 2024 12:08 28s main
main
April 6, 2024 12:08 28s
Fix fused models for tf >= 4.39 (#418) Documentation #22: Commit 5d7b050 pushed by casper-hansen
April 6, 2024 12:06 48s main
main
April 6, 2024 12:06 48s
Bump to v0.2.4 (#409) Documentation #21: Commit 0fa9a2c pushed by casper-hansen
March 24, 2024 11:26 28s main
main
March 24, 2024 11:26 28s
Pin transformers>=4.35.0,<=4.38.2 (#408) Documentation #20: Commit 0f94218 pushed by casper-hansen
March 24, 2024 11:24 27s main
main
March 24, 2024 11:24 27s
Add Gemma Support (#393) Documentation #19: Commit 94e73f0 pushed by casper-hansen
March 11, 2024 14:15 32s main
main
March 11, 2024 14:15 32s
Bump to 0.2.3 Documentation #18: Commit d8ca1e2 pushed by casper-hansen
March 2, 2024 10:13 29s main
main
March 2, 2024 10:13 29s
x_max -> x_mean and w_max -> w_mean name changes and some comments (#… Documentation #17: Commit f713b88 pushed by casper-hansen
March 2, 2024 10:11 30s main
main
March 2, 2024 10:11 30s
Fix double bias (#383) Documentation #16: Commit d9dc8e5 pushed by casper-hansen
March 2, 2024 10:11 27s main
main
March 2, 2024 10:11 27s
New optimized kernels (#365) Documentation #15: Commit 68c727a pushed by casper-hansen
February 24, 2024 23:01 27s main
main
February 24, 2024 23:01 27s
Bump to 0.2.2 (#356) Documentation #14: Commit 6b7992a pushed by casper-hansen
February 17, 2024 10:37 30s main
main
February 17, 2024 10:37 30s
Remove MoE Triton kernels (#355) Documentation #13: Commit a40515f pushed by casper-hansen
February 17, 2024 10:34 27s main
main
February 17, 2024 10:34 27s
Add multi-GPU benchmark of Mixtral (#353) Documentation #12: Commit d54bf0e pushed by casper-hansen
February 16, 2024 17:18 1m 8s main
main
February 16, 2024 17:18 1m 8s
Support Fused Mixtral on multi-GPU (#352) Documentation #11: Commit 79b6fbd pushed by casper-hansen
February 16, 2024 15:13 28s main
main
February 16, 2024 15:13 28s
Bump to 0.2.1 (#351) Documentation #10: Commit 7405310 pushed by casper-hansen
February 16, 2024 08:59 30s main
main
February 16, 2024 08:59 30s
Fix triton dependency (#350) Documentation #9: Commit 8849043 pushed by casper-hansen
February 16, 2024 08:41 29s main
main
February 16, 2024 08:41 29s
ENH / FIX: Few enhancements and fix for mixed-precision training (#348) Documentation #8: Commit 969b290 pushed by casper-hansen
February 16, 2024 08:38 26s main
main
February 16, 2024 08:38 26s
Avoid downloading ROCm (#347) Documentation #7: Commit 2de6092 pushed by casper-hansen
February 15, 2024 21:16 26s main
main
February 15, 2024 21:16 26s