Skip to content

Actions: ggml-org/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
6,697 workflow run results
6,697 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922) Publish Docker image #14370: Commit 2a24c8c pushed by slaren
August 16, 2024 02:23 3h 16m 28s master
master
August 16, 2024 02:23 3h 16m 28s
ggml : dynamic ggml_sched_max_splits based on graph_size (#9047) Publish Docker image #14369: Commit e3f6fd5 pushed by slaren
August 16, 2024 02:22 2h 51m 33s master
master
August 16, 2024 02:22 2h 51m 33s
retrieval : fix memory leak in retrieval query handling (#8955) Publish Docker image #14368: Commit 4b9afbb pushed by ggerganov
August 15, 2024 07:40 4h 46m 54s master
master
August 15, 2024 07:40 4h 46m 54s
server : fix duplicated n_predict key in the generation_settings (#8994) Publish Docker image #14367: Commit 37501d9 pushed by ggerganov
August 15, 2024 07:28 4h 4m 1s master
master
August 15, 2024 07:28 4h 4m 1s
common : remove duplicate function llama_should_add_bos_token (#8778) Publish Docker image #14366: Commit 4af8420 pushed by ggerganov
August 15, 2024 07:23 3h 42m 11s master
master
August 15, 2024 07:23 3h 42m 11s
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850) Publish Docker image #14365: Commit 6bda7ce pushed by ggerganov
August 15, 2024 07:17 2h 30m 6s master
master
August 15, 2024 07:17 2h 30m 6s
server : init stop and error fields of the result struct (#9026) Publish Docker image #14364: Commit 234b306 pushed by ggerganov
August 15, 2024 06:22 2h 49m 32s master
master
August 15, 2024 06:22 2h 49m 32s
Vulkan Optimizations and Fixes (#8959) Publish Docker image #14363: Commit 5fd89a7 pushed by 0cc4m
August 14, 2024 16:32 2h 39m 22s master
master
August 14, 2024 16:32 2h 39m 22s
server : fix segfault on long system prompt (#8987) Publish Docker image #14362: Commit 98a532d pushed by ggerganov
August 14, 2024 06:51 3h 19m 58s master
master
August 14, 2024 06:51 3h 19m 58s
cmake : remove unused option GGML_CURL (#9011) Publish Docker image #14361: Commit 43bdd3c pushed by ggerganov
August 14, 2024 06:14 2h 56m 10s master
master
August 14, 2024 06:14 2h 56m 10s
ggml : move rope type enum to ggml.h (#8949) Publish Docker image #14360: Commit 06943a6 pushed by slaren
August 13, 2024 19:13 2h 58m 49s master
master
August 13, 2024 19:13 2h 58m 49s
export-lora : throw error if lora is quantized (#9002) Publish Docker image #14359: Commit 828d6ff pushed by ngxson
August 13, 2024 09:41 2h 38m 5s master
master
August 13, 2024 09:41 2h 38m 5s
llama : model-based max number of graph nodes calculation (#8970) Publish Docker image #14358: Commit 0fd93cd pushed by slaren
August 12, 2024 15:14 3h 35m 16s master
master
August 12, 2024 15:14 3h 35m 16s
grammar-parser : fix possible null-deref (#9004) Publish Docker image #14357: Commit 1262e7e pushed by ggerganov
August 12, 2024 12:36 3h 59m 6s master
master
August 12, 2024 12:36 3h 59m 6s
ggml: fix div-by-zero (#9003) Publish Docker image #14356: Commit df5478f pushed by slaren
August 12, 2024 12:21 3h 11m 55s master
master
August 12, 2024 12:21 3h 11m 55s
Fix a spelling mistake (#9001) Publish Docker image #14355: Commit 2589292 pushed by JohannesGaessler
August 12, 2024 09:46 3h 46m 44s master
master
August 12, 2024 09:46 3h 46m 44s
server : handle models with missing EOS token (#8997) Publish Docker image #14354: Commit 5ef07e2 pushed by ggerganov
August 12, 2024 07:21 3h 0m 56s master
master
August 12, 2024 07:21 3h 0m 56s
llama : check all graph nodes when searching for result_embd_pooled (… Publish Docker image #14353: Commit 33309f6 pushed by fairydreaming
August 11, 2024 08:35 3h 24m 48s master
master
August 11, 2024 08:35 3h 24m 48s
Optimize Vulkan backend for better CPU performance and less GPU synch… Publish Docker image #14352: Commit 7c5bfd5 pushed by 0cc4m
August 11, 2024 08:09 2h 29m 39s master
master
August 11, 2024 08:09 2h 29m 39s
metal : fix uninitialized abort_callback (#8968) Publish Docker image #14351: Commit 6e02327 pushed by slaren
August 10, 2024 13:42 3h 12m 35s master
master
August 10, 2024 13:42 3h 12m 35s
llama : default n_swa for phi-3 (#8931) Publish Docker image #14350: Commit 7eb2384 pushed by ngxson
August 10, 2024 11:04 2h 45m 1s master
master
August 10, 2024 11:04 2h 45m 1s
Add support for encoder-only T5 models (#8900) Publish Docker image #14349: Commit 7c3f55c pushed by fairydreaming
August 10, 2024 09:43 2h 38m 37s master
master
August 10, 2024 09:43 2h 38m 37s
Merge commit from fork Publish Docker image #14348: Commit b72942f pushed by ggerganov
August 9, 2024 20:03 2h 37m 43s master
master
August 9, 2024 20:03 2h 37m 43s
llama : add support for lora adapters in T5 model (#8938) Publish Docker image #14347: Commit 6afd1a9 pushed by fairydreaming
August 9, 2024 16:53 2h 47m 20s master
master
August 9, 2024 16:53 2h 47m 20s
make : fix llava obj file race (#8946) Publish Docker image #14346: Commit 272e3bd pushed by ggerganov
August 9, 2024 15:24 3h 32m 1s master
master
August 9, 2024 15:24 3h 32m 1s