Skip to content

Actions: vectorch-ai/ScaleLLM

Build and test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
867 workflow runs
867 workflow runs

Filter by Event

Loading

Filter by Status

Loading

Filter by Branch

Loading

Filter by Actor

Loading
fix intermediate_size for qwen model loader.
Build and test #48: Commit 358bfbb pushed by guocuimi
December 27, 2023 02:40 6m 35s main
December 27, 2023 02:40 6m 35s
added qwen model support. (pending tokenizer support)
Build and test #47: Commit 793e664 pushed by guocuimi
December 27, 2023 02:17 6m 31s main
December 27, 2023 02:17 6m 31s
added chat template for chatglm
Build and test #46: Commit 926a06c pushed by guocuimi
December 26, 2023 12:49 6m 25s main
December 26, 2023 12:49 6m 25s
added chatglm model support. (pending testing)
Build and test #45: Commit bc1aba7 pushed by guocuimi
December 26, 2023 08:26 11m 18s main
December 26, 2023 08:26 11m 18s
[refactor] rename Executor to ThreadPool. (#36)
Build and test #44: Commit 7735b24 pushed by liutongxuan
December 22, 2023 03:09 20m 8s main
December 22, 2023 03:09 20m 8s
added inja (header-only library) template engine to parse chat template.
Build and test #42: Commit c49066d pushed by guocuimi
December 10, 2023 07:13 15m 1s main
December 10, 2023 07:13 15m 1s
moved top_p and top_k into sampler
Build and test #41: Commit b9afdb9 pushed by guocuimi
December 8, 2023 06:45 6m 32s main
December 8, 2023 06:45 6m 32s
added topp_sampling kernel
Build and test #40: Commit 35375ae pushed by guocuimi
December 7, 2023 19:32 7m 51s main
December 7, 2023 19:32 7m 51s
enable logits processor kernels for FrequencyPresencePenalty and Repe…
Build and test #39: Commit 9257567 pushed by guocuimi
December 7, 2023 05:01 6m 40s main
December 7, 2023 05:01 6m 40s
pass in token count directly to avoid using bincout in FrequencyPrese…
Build and test #38: Commit f9755e7 pushed by guocuimi
December 6, 2023 05:19 6m 30s main
December 6, 2023 05:19 6m 30s
added meaningful error messages into response.
Build and test #37: Commit 9c92351 pushed by guocuimi
December 5, 2023 21:13 6m 34s main
December 5, 2023 21:13 6m 34s
moved model_downloader into simpler.cpp
Build and test #36: Commit 6580956 pushed by guocuimi
December 5, 2023 20:59 6m 33s main
December 5, 2023 20:59 6m 33s
[refactor] move hf model download logic into seperate python file; i…
Build and test #35: Commit 8d30cfe pushed by guocuimi
December 4, 2023 23:58 6m 31s main
December 4, 2023 23:58 6m 31s
[bug fix] avoid returning stop tokens in response.
Build and test #34: Commit bb329ec pushed by guocuimi
December 3, 2023 17:46 6m 30s main
December 3, 2023 17:46 6m 30s
added exception handling logic for http server to handle partial requ…
Build and test #33: Commit 30ad6fc pushed by guocuimi
November 30, 2023 18:04 7m 0s main
November 30, 2023 18:04 7m 0s
misc bug fixes: 1> bug fix for model loader, 2> yi chat template
Build and test #32: Commit 376875c pushed by guocuimi
November 23, 2023 20:24 7m 8s main
November 23, 2023 20:24 7m 8s
added chat model support for yi
Build and test #31: Commit 68854da pushed by guocuimi
November 23, 2023 11:47 8m 19s main
November 23, 2023 11:47 8m 19s
added boost dependency to fix build error.
Build and test #30: Commit 586856d pushed by guocuimi
November 22, 2023 18:27 15m 13s main
November 22, 2023 18:27 15m 13s
replaced libevhtp with boost asio for http server to avoid epoll_wait…
Build and test #29: Commit 66e016d pushed by guocuimi
November 22, 2023 08:42 10m 32s main
November 22, 2023 08:42 10m 32s
use temperature_penalty kernel for temperature logits processor
Build and test #28: Commit 3ddaa44 pushed by guocuimi
November 22, 2023 01:44 7m 28s main
November 22, 2023 01:44 7m 28s
added args overrider that allows override any model args with command…
Build and test #27: Commit 7e89647 pushed by guocuimi
November 22, 2023 00:06 15m 6s main
November 22, 2023 00:06 15m 6s
added 'disable_custom_kernels' gflags to allow disable all custom ker…
Build and test #26: Commit 149b943 pushed by guocuimi
November 11, 2023 23:32 7m 56s main
November 11, 2023 23:32 7m 56s
fix: always use float32 for cpu.
Build and test #25: Commit bb73a8c pushed by guocuimi
November 9, 2023 23:14 7m 10s main
November 9, 2023 23:14 7m 10s
misc: added chat api column in supported models and only build scalel…
Build and test #23: Commit e5c53ff pushed by guocuimi
November 9, 2023 16:59 9m 1s main
November 9, 2023 16:59 9m 1s
ProTip! You can narrow down the results and go further in time using created:<2023-11-09 or the other filters available.