Skip to content

Actions: ggml-org/llama.cpp

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
3,224 workflow run results
3,224 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add ring buffer to store prev tokens in sampling
Pull Request Labeler #3075: Pull request #8890 synchronize by kylo5aby
August 12, 2024 01:54 12m 21s
August 12, 2024 01:54 12m 21s
llama : support raw NUL bytes in tokens
Pull Request Labeler #3074: Pull request #8992 opened by compilade
August 12, 2024 01:33 9m 20s
August 12, 2024 01:33 9m 20s
llama : support RWKV v6 models
Pull Request Labeler #3073: Pull request #8980 synchronize by MollySophia
August 12, 2024 01:30 13s
August 12, 2024 01:30 13s
llama : support RWKV v6 models
Pull Request Labeler #3072: Pull request #8980 synchronize by MollySophia
August 12, 2024 01:13 16s
August 12, 2024 01:13 16s
llama : support RWKV v6 models
Pull Request Labeler #3071: Pull request #8980 synchronize by MollySophia
August 12, 2024 01:12 19s
August 12, 2024 01:12 19s
llama : support RWKV v6 models
Pull Request Labeler #3070: Pull request #8980 synchronize by MollySophia
August 12, 2024 01:09 15s
August 12, 2024 01:09 15s
feat: whitelist jina bert v2 for llama-server embedding
Pull Request Labeler #3069: Pull request #8989 opened by wsxiaoys
August 12, 2024 00:06 20s
August 12, 2024 00:06 20s
tests : add integration test for lora adapters
Pull Request Labeler #3068: Pull request #8957 synchronize by ltoniazzi
August 11, 2024 23:34 14s
August 11, 2024 23:34 14s
tests : add integration test for lora adapters
Pull Request Labeler #3067: Pull request #8957 synchronize by ltoniazzi
August 11, 2024 23:21 14s
August 11, 2024 23:21 14s
Changes for the existing quant strategies / FTYPEs and new ones
Pull Request Labeler #3066: Pull request #8836 synchronize by Nexesenex
August 11, 2024 19:49 20s
August 11, 2024 19:49 20s
Changes for the existing quant strategies / FTYPEs and new ones
Pull Request Labeler #3065: Pull request #8836 synchronize by Nexesenex
August 11, 2024 19:44 18s
August 11, 2024 19:44 18s
server : fix segfault on long system prompt
Pull Request Labeler #3064: Pull request #8987 opened by compilade
August 11, 2024 18:37 15s
August 11, 2024 18:37 15s
Revert "ggml : remove OpenCL (#7735) + (#8235)"
Pull Request Labeler #3063: Pull request #8986 opened by okias
August 11, 2024 15:47 17s
August 11, 2024 15:47 17s
Changes for the existing quant strategies / FTYPEs and new ones
Pull Request Labeler #3062: Pull request #8836 synchronize by Nexesenex
August 11, 2024 14:46 17s
August 11, 2024 14:46 17s
Changes for the existing quant strategies / FTYPEs and new ones
Pull Request Labeler #3061: Pull request #8836 synchronize by Nexesenex
August 11, 2024 14:41 15s
August 11, 2024 14:41 15s
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model.
Pull Request Labeler #3060: Pull request #8984 synchronize by cyzero-kim
August 11, 2024 12:29 13s
August 11, 2024 12:29 13s
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model.
Pull Request Labeler #3059: Pull request #8984 opened by cyzero-kim
August 11, 2024 10:39 14m 30s
August 11, 2024 10:39 14m 30s
py : fix requirements check '==' -> '~='
Pull Request Labeler #3058: Pull request #8982 synchronize by ggerganov
August 11, 2024 09:05 1h 46m 29s
August 11, 2024 09:05 1h 46m 29s
Vulkan Optimizations and Fixes
Pull Request Labeler #3057: Pull request #8959 synchronize by 0cc4m
August 11, 2024 08:58 1h 33m 47s
August 11, 2024 08:58 1h 33m 47s
llama : refactor sampling
Pull Request Labeler #3056: Pull request #8643 synchronize by ggerganov
August 11, 2024 08:44 1h 13m 33s
August 11, 2024 08:44 1h 13m 33s
py : fix requirements check '==' -> '~='
Pull Request Labeler #3055: Pull request #8982 opened by ggerganov
August 11, 2024 08:16 1h 10m 6s
August 11, 2024 08:16 1h 10m 6s
ggml : move rope type enum to ggml.h
Pull Request Labeler #3054: Pull request #8949 synchronize by danbev
August 11, 2024 08:14 1h 1m 56s
August 11, 2024 08:14 1h 1m 56s
Optimize Vulkan backend for better CPU performance and less GPU synchronization overhead.
Pull Request Labeler #3053: Pull request #8943 synchronize by 0cc4m
August 11, 2024 07:40 14s
August 11, 2024 07:40 14s
ggml : move rope type enum to ggml.h
Pull Request Labeler #3052: Pull request #8949 synchronize by danbev
August 11, 2024 06:53 12s
August 11, 2024 06:53 12s
ggml : move rope type enum to ggml.h
Pull Request Labeler #3051: Pull request #8949 synchronize by danbev
August 11, 2024 06:18 4m 36s
August 11, 2024 06:18 4m 36s