Skip to content

Actions: jiqing-feng/optimum-intel

Offline - Test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
22 workflow runs
22 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Enable Text2text task on ipex (#1054)
Offline - Test #22: Commit a76be08 pushed by jiqing-feng
December 18, 2024 04:37 4m 13s main
December 18, 2024 04:37 4m 13s
Update readme (#1066)
Offline - Test #21: Commit 35cf1d2 pushed by jiqing-feng
December 16, 2024 01:54 4m 22s main
December 16, 2024 01:54 4m 22s
Update backup-precision option description (#1055)
Offline - Test #20: Commit 41d9a37 pushed by jiqing-feng
December 11, 2024 08:05 4m 22s main
December 11, 2024 08:05 4m 22s
ipex Page attn xpu support bug fix (#1053)
Offline - Test #19: Commit 6ea6b5d pushed by jiqing-feng
December 10, 2024 08:51 4m 22s main
December 10, 2024 08:51 4m 22s
Add INC layerwise quantization support (#1018)
Offline - Test #18: Commit 4d73e51 pushed by jiqing-feng
December 9, 2024 02:36 4m 57s main
December 9, 2024 02:36 4m 57s
Relax OpenVINO dependency version (#1005)
Offline - Test #17: Commit 6a3b1ba pushed by jiqing-feng
November 26, 2024 03:01 3m 58s main
November 26, 2024 03:01 3m 58s
fix switching between legacy and new processing for llava (#970)
Offline - Test #16: Commit c887610 pushed by jiqing-feng
November 11, 2024 08:44 3m 52s main
November 11, 2024 08:44 3m 52s
Clean and clear CI (#975)
Offline - Test #15: Commit d357376 pushed by jiqing-feng
November 6, 2024 01:25 4m 13s main
November 6, 2024 01:25 4m 13s
Add nncf and ov nightly for slow tests (#922)
Offline - Test #14: Commit 785e1a6 pushed by jiqing-feng
October 9, 2024 02:59 3m 58s main
October 9, 2024 02:59 3m 58s
replaced numa with py-libnuma to work w python 3.11 (#900)
Offline - Test #13: Commit b760a1d pushed by jiqing-feng
September 18, 2024 02:46 4m 13s main
September 18, 2024 02:46 4m 13s
Add support assisted decoding in ipex 2.4 (#823)
Offline - Test #12: Commit 5db1ac7 pushed by jiqing-feng
September 10, 2024 05:19 3m 43s main
September 10, 2024 05:19 3m 43s
set cpu affinity and membind for better oob performance (#853)
Offline - Test #11: Commit 9a18ae0 pushed by jiqing-feng
August 28, 2024 06:45 3m 32s main
August 28, 2024 06:45 3m 32s
Fix bf16 inference accuracy for mistral, phi3, dbrx (#833)
Offline - Test #10: Commit 31430d6 pushed by jiqing-feng
July 26, 2024 06:43 4m 0s main
July 26, 2024 06:43 4m 0s
Fix loading models from cache (#820)
Offline - Test #9: Commit 9ef6766 pushed by jiqing-feng
July 15, 2024 01:10 3m 56s main
July 15, 2024 01:10 3m 56s
Increase default 4-bit compression ratio from 0.8 to 1.0 (#805)
Offline - Test #8: Commit eac1f6c pushed by jiqing-feng
July 9, 2024 06:16 5m 3s main
July 9, 2024 06:16 5m 3s
Deprecate onnx/ort model export and quantization (#795)
Offline - Test #7: Commit 384dda5 pushed by jiqing-feng
July 2, 2024 00:41 3m 50s main
July 2, 2024 00:41 3m 50s
Add openvino export documentation (#765)
Offline - Test #6: Commit c1ee8ac pushed by jiqing-feng
June 26, 2024 03:08 4m 8s main
June 26, 2024 03:08 4m 8s
Update export function path for neural-compressor v2.6 (#777)
Offline - Test #5: Commit f935233 pushed by jiqing-feng
June 25, 2024 07:58 4m 16s main
June 25, 2024 07:58 4m 16s
Fix openvino quantization config (#773)
Offline - Test #4: Commit 80e9bf6 pushed by jiqing-feng
June 24, 2024 06:25 5m 13s main
June 24, 2024 06:25 5m 13s
Fix IPEXModel input names for nn.module (#775)
Offline - Test #3: Commit ef23a5d pushed by jiqing-feng
June 21, 2024 01:53 3m 43s main
June 21, 2024 01:53 3m 43s
Refactor CPU llama inference code (#728)
Offline - Test #2: Commit 36e5b23 pushed by jiqing-feng
June 7, 2024 08:21 4m 9s main
June 7, 2024 08:21 4m 9s
fix olmo accuracy for bf16, add sdpa for persimmon, support jais (#726)
Offline - Test #1: Commit 1ab78d5 pushed by jiqing-feng
June 7, 2024 01:07 5m 42s main
June 7, 2024 01:07 5m 42s