Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Actions: intel/neural-speed

Python Unit Test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
266 workflow run results
266 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support gptq with solar
Python Unit Test #219: Pull request #106 opened by a32543254
February 1, 2024 07:26 10m 45s gptq_solar
February 1, 2024 07:26 10m 45s
update profling log when NS_PROFILING is OFF
Python Unit Test #218: Pull request #102 synchronize by zhenwei-intel
February 1, 2024 00:13 15m 12s lzw/update_log
February 1, 2024 00:13 15m 12s
Yarn feature
Python Unit Test #217: Pull request #97 synchronize by xiguiw
January 31, 2024 09:33 7m 11s xiguiw:yarn-feature
January 31, 2024 09:33 7m 11s
Optimization of Layernormalization
Python Unit Test #216: Pull request #103 synchronize by luoyu-intel
January 31, 2024 07:41 2h 29m 37s ort_patch
January 31, 2024 07:41 2h 29m 37s
Optimization of Layernormalization
Python Unit Test #215: Pull request #103 synchronize by luoyu-intel
January 31, 2024 07:32 9m 45s ort_patch
January 31, 2024 07:32 9m 45s
Optimization of Layernormalization
Python Unit Test #214: Pull request #103 opened by luoyu-intel
January 31, 2024 07:10 21m 36s ort_patch
January 31, 2024 07:10 21m 36s
Support Solar 10.7B
Python Unit Test #213: Pull request #101 synchronize by a32543254
January 31, 2024 06:51 2h 44m 44s enable_solar
January 31, 2024 06:51 2h 44m 44s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #212: Pull request #100 synchronize by Zhenzhong1
January 31, 2024 06:51 2h 28m 40s zhenzhong/gptq-gptj
January 31, 2024 06:51 2h 28m 40s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #211: Pull request #100 synchronize by Zhenzhong1
January 31, 2024 06:46 4m 18s zhenzhong/gptq-gptj
January 31, 2024 06:46 4m 18s
update profling log when NS_PROFILING is OFF
Python Unit Test #210: Pull request #102 opened by zhenwei-intel
January 31, 2024 06:44 1h 43m 7s lzw/update_log
January 31, 2024 06:44 1h 43m 7s
Support Solar 10.7B
Python Unit Test #209: Pull request #101 opened by a32543254
January 31, 2024 06:28 23m 20s enable_solar
January 31, 2024 06:28 23m 20s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #208: Pull request #100 synchronize by Zhenzhong1
January 31, 2024 05:46 1h 0m 13s zhenzhong/gptq-gptj
January 31, 2024 05:46 1h 0m 13s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #207: Pull request #100 synchronize by Zhenzhong1
January 31, 2024 05:35 11m 53s zhenzhong/gptq-gptj
January 31, 2024 05:35 11m 53s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #205: Pull request #100 synchronize by Zhenzhong1
January 30, 2024 10:13 7m 18s zhenzhong/gptq-gptj
January 30, 2024 10:13 7m 18s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #204: Pull request #100 synchronize by Zhenzhong1
January 30, 2024 09:13 7m 32s zhenzhong/gptq-gptj
January 30, 2024 09:13 7m 32s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #203: Pull request #100 synchronize by Zhenzhong1
January 30, 2024 07:02 7m 17s zhenzhong/gptq-gptj
January 30, 2024 07:02 7m 17s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #202: Pull request #100 synchronize by Zhenzhong1
January 30, 2024 04:41 7m 17s zhenzhong/gptq-gptj
January 30, 2024 04:41 7m 17s
[LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j
Python Unit Test #201: Pull request #100 opened by Zhenzhong1
January 30, 2024 03:54 9m 11s zhenzhong/gptq-gptj
January 30, 2024 03:54 9m 11s
[LLM Runtime] Support loading models from HF directly.
Python Unit Test #198: Pull request #93 synchronize by Zhenzhong1
January 25, 2024 09:25 7m 10s zhenzhong/online_load
January 25, 2024 09:25 7m 10s
[LLM Runtime] Support loading models from HF directly.
Python Unit Test #197: Pull request #93 synchronize by Zhenzhong1
January 25, 2024 09:08 7m 13s zhenzhong/online_load
January 25, 2024 09:08 7m 13s
[LLM Runtime] Support loading models from HF directly.
Python Unit Test #196: Pull request #93 opened by Zhenzhong1
January 25, 2024 07:52 7m 16s zhenzhong/online_load
January 25, 2024 07:52 7m 16s
Cont batching mha++
Python Unit Test #195: Pull request #89 synchronize by DDEle
January 25, 2024 05:57 7m 16s cont_batching_mha++
January 25, 2024 05:57 7m 16s
[LLM Runtime] Enable phi-2&phi-1.5&phi-1
Python Unit Test #194: Pull request #78 synchronize by intellinjun
January 25, 2024 02:11 7m 11s phi2
January 25, 2024 02:11 7m 11s
[LLM Runtime] Enable phi-2&phi-1.5&phi-1
Python Unit Test #193: Pull request #78 synchronize by intellinjun
January 25, 2024 02:08 3m 39s phi2
January 25, 2024 02:08 3m 39s
[Neural Speed] Cont Batching in Offline and Server (GPT-J & Beam Search First)
Python Unit Test #192: Pull request #69 synchronize by DDEle
January 24, 2024 09:01 9m 37s cont_batching
January 24, 2024 09:01 9m 37s