Skip to content

Actions: ggerganov/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
9,025 workflow run results
9,025 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[SYCL] Re-enabled mul_mat_batched_sycl (#8095) CI #13236: Commit 083bacc pushed by airMeng
June 25, 2024 02:19 2h 21m 28s master
master
June 25, 2024 02:19 2h 21m 28s
Extend llm_build_ffn() to support _scale tensors CI #13235: Pull request #8103 opened by Eddie-Wang1120
June 25, 2024 01:42 2h 23m 3s Eddie-Wang1120:ffn_change
Eddie-Wang1120:ffn_change
June 25, 2024 01:42 2h 23m 3s
json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum CI #13234: Pull request #7797 synchronize by ochafik
June 25, 2024 01:11 2h 16m 11s ochafik:json-bounds2
ochafik:json-bounds2
June 25, 2024 01:11 2h 16m 11s
json: fix additionalProperties, allow space after enum/const CI #13233: Pull request #7840 synchronize by ochafik
June 25, 2024 00:43 2h 4m 10s ochafik:json-additional
ochafik:json-additional
June 25, 2024 00:43 2h 4m 10s
gfx1010 optimizations CI #13232: Pull request #8085 synchronize by daniandtheweb
June 25, 2024 00:15 1h 59m 38s daniandtheweb:gfx1010_optimizations
daniandtheweb:gfx1010_optimizations
June 25, 2024 00:15 1h 59m 38s
[SYCL] Re-enabled mul_mat_batched_sycl CI #13231: Pull request #8095 synchronize by airMeng
June 25, 2024 00:09 1h 36m 1s sycl-mul-mat-batched
sycl-mul-mat-batched
June 25, 2024 00:09 1h 36m 1s
CUDA: fix matrix multiplication algorithm choice (#8102) CI #13230: Commit 2df373a pushed by JohannesGaessler
June 24, 2024 23:22 3h 19m 7s master
master
June 24, 2024 23:22 3h 19m 7s
json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum CI #13229: Pull request #7797 synchronize by ochafik
June 24, 2024 22:44 1h 52m 50s ochafik:json-bounds2
ochafik:json-bounds2
June 24, 2024 22:44 1h 52m 50s
CUDA: fix matrix multiplication algorithm choice CI #13228: Pull request #8102 opened by JohannesGaessler
June 24, 2024 20:39 3h 26m 45s JohannesGaessler:cuda-fix-matrix-selection
JohannesGaessler:cuda-fix-matrix-selection
June 24, 2024 20:39 3h 26m 45s
json: fix additionalProperties, allow space after enum/const CI #13227: Pull request #7840 synchronize by ochafik
June 24, 2024 20:31 3h 6m 41s ochafik:json-additional
ochafik:json-additional
June 24, 2024 20:31 3h 6m 41s
json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum CI #13226: Pull request #7797 synchronize by ochafik
June 24, 2024 20:29 2h 15m 15s ochafik:json-bounds2
ochafik:json-bounds2
June 24, 2024 20:29 2h 15m 15s
json: better support for "type" unions (e.g. nullable arrays w/ typed items) CI #13225: Pull request #7863 synchronize by ochafik
June 24, 2024 20:20 2h 39m 53s ochafik:json-type
ochafik:json-type
June 24, 2024 20:20 2h 39m 53s
Add Unigram tokenizer needed by T5 and FLAN-T5 model families CI #13224: Pull request #8089 synchronize by fairydreaming
June 24, 2024 19:39 2h 38m 1s fairydreaming:t5-clean-2
fairydreaming:t5-clean-2
June 24, 2024 19:39 2h 38m 1s
llama : reorganize source code + improve CMake CI #13223: Pull request #8006 synchronize by ggerganov
June 24, 2024 19:06 2h 16m 50s gg/reorganize-project
gg/reorganize-project
June 24, 2024 19:06 2h 16m 50s
CUDA: fix MMQ writeback for int8 tensor cores CI #13222: Pull request #8100 opened by JohannesGaessler
June 24, 2024 18:58 1h 51m 10s JohannesGaessler:cuda-fix-mmq-writeback
JohannesGaessler:cuda-fix-mmq-writeback
June 24, 2024 18:58 1h 51m 10s
Detokenizer fixes CI #13221: Pull request #8039 synchronize by jaime-m-p
June 24, 2024 18:56 1h 39m 53s jaime-m-p:detokenizer
jaime-m-p:detokenizer
June 24, 2024 18:56 1h 39m 53s
Streamline embeddings from "non-embedding" models CI #13220: Pull request #8087 synchronize by iamlemec
June 24, 2024 16:54 3h 17m 38s iamlemec:attention-type
iamlemec:attention-type
June 24, 2024 16:54 3h 17m 38s
gfx1010 optimizations CI #13219: Pull request #8085 synchronize by daniandtheweb
June 24, 2024 16:49 2h 48m 16s daniandtheweb:gfx1010_optimizations
daniandtheweb:gfx1010_optimizations
June 24, 2024 16:49 2h 48m 16s
CUDA: use MMQ instead of cuBLAS by default (#8075) CI #13218: Commit a818f30 pushed by JohannesGaessler
June 24, 2024 15:43 4h 3m 39s master
master
June 24, 2024 15:43 4h 3m 39s
gfx1010 optimizations CI #13217: Pull request #8085 synchronize by daniandtheweb
June 24, 2024 14:47 2h 2m 22s daniandtheweb:gfx1010_optimizations
daniandtheweb:gfx1010_optimizations
June 24, 2024 14:47 2h 2m 22s
llama : reorganize source code + improve CMake CI #13216: Pull request #8006 synchronize by ggerganov
June 24, 2024 13:54 2h 44m 1s gg/reorganize-project
gg/reorganize-project
June 24, 2024 13:54 2h 44m 1s
llama : reorganize source code + improve CMake CI #13215: Pull request #8006 synchronize by ggerganov
June 24, 2024 13:51 2m 35s gg/reorganize-project
gg/reorganize-project
June 24, 2024 13:51 2m 35s
[SYCL] Re-enabled mul_mat_batched_sycl CI #13214: Pull request #8095 opened by airMeng
June 24, 2024 12:57 2h 57m 7s sycl-mul-mat-batched
sycl-mul-mat-batched
June 24, 2024 12:57 2h 57m 7s
CUDA: use MMQ instead of cuBLAS by default CI #13213: Pull request #8075 synchronize by JohannesGaessler
June 24, 2024 12:35 2h 39m 20s JohannesGaessler:cuda-mmq-default
JohannesGaessler:cuda-mmq-default
June 24, 2024 12:35 2h 39m 20s
llama : return nullptr from llama_grammar_init CI #13212: Pull request #8093 opened by danbev
June 24, 2024 11:25 1h 46m 34s danbev:grammar-init-return-null
danbev:grammar-init-return-null
June 24, 2024 11:25 1h 46m 34s