Skip to content

Actions: ggerganov/llama.cpp

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
8,457 workflow run results
8,457 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : add some missing env variables (#9116)
Publish Docker image #14404: Commit a77feb5 pushed by ngxson
August 27, 2024 09:07 1h 40m 20s master
August 27, 2024 09:07 1h 40m 20s
llama : fix ChatGLM4 wrong shape (#9194)
Publish Docker image #14403: Commit 2e59d61 pushed by ggerganov
August 27, 2024 06:58 1h 2m 21s master
August 27, 2024 06:58 1h 2m 21s
llama : fix llama3.1 rope_freqs not respecting custom head_dim (#9141)
Publish Docker image #14402: Commit 75e1dbb pushed by ggerganov
August 27, 2024 06:53 1h 38m 49s master
August 27, 2024 06:53 1h 38m 49s
common : Update stb_image.h to latest version (#9161)
Publish Docker image #14401: Commit ad76569 pushed by ggerganov
August 27, 2024 05:58 1h 39m 37s master
August 27, 2024 05:58 1h 39m 37s
ggml : do not crash when quantizing q4_x_x with an imatrix (#9192)
Publish Docker image #14400: Commit 7d787ed pushed by slaren
August 26, 2024 17:44 1h 40m 1s master
August 26, 2024 17:44 1h 40m 1s
metal : separate scale and mask from QKT in FA kernel (#9189)
Publish Docker image #14399: Commit 06658ad pushed by ggerganov
August 26, 2024 15:31 2h 53m 51s master
August 26, 2024 15:31 2h 53m 51s
ggml : add SSM Metal kernels (#8546)
Publish Docker image #14398: Commit fc18425 pushed by ggerganov
August 26, 2024 14:55 2h 1m 50s master
August 26, 2024 14:55 2h 1m 50s
tests : fix compile warnings for unreachable code (#9185)
Publish Docker image #14397: Commit 879275a pushed by ggerganov
August 26, 2024 13:30 1h 58m 59s master
August 26, 2024 13:30 1h 58m 59s
metal : gemma2 flash attention support (#9159)
Publish Docker image #14396: Commit 0c41e03 pushed by slaren
August 26, 2024 09:09 2h 7m 24s master
August 26, 2024 09:09 2h 7m 24s
llama : fix time complexity of string replacement (#9163)
Publish Docker image #14395: Commit 436787f pushed by ggerganov
August 26, 2024 06:09 6h 5m 10s master
August 26, 2024 06:09 6h 5m 10s
common: fixed not working find argument --n-gpu-layers-draft (#9175)
Publish Docker image #14394: Commit 93bc383 pushed by JohannesGaessler
August 25, 2024 22:54 1h 36m 58s master
August 25, 2024 22:54 1h 36m 58s
CUDA: fix Gemma 2 numerical issues for FA (#9166)
Publish Docker image #14393: Commit f91fc56 pushed by JohannesGaessler
August 25, 2024 20:11 1h 44m 37s master
August 25, 2024 20:11 1h 44m 37s
CPU/CUDA: Gemma 2 FlashAttention support (#8542)
Publish Docker image #14392: Commit e11bd85 pushed by JohannesGaessler
August 24, 2024 19:35 1h 37m 54s master
August 24, 2024 19:35 1h 37m 54s
quantize : fix typo in usage help of quantize.cpp (#9145)
Publish Docker image #14391: Commit 8f824ff pushed by ggerganov
August 24, 2024 06:22 2h 35m 51s master
August 24, 2024 06:22 2h 35m 51s
llama : use F32 precision in GLM4 attention and no FA (#9130)
Publish Docker image #14390: Commit a07c32e pushed by ggerganov
August 23, 2024 07:27 2h 54m 25s master
August 23, 2024 07:27 2h 54m 25s
[SYCL] Add a space to supress a cmake warning (#9133)
Publish Docker image #14389: Commit 11b84eb pushed by airMeng
August 22, 2024 14:09 2h 30m 29s master
August 22, 2024 14:09 2h 30m 29s
[SYCL] Add oneDNN primitive support (#9091)
Publish Docker image #14388: Commit 1731d42 pushed by airMeng
August 22, 2024 04:50 2h 31m 28s master
August 22, 2024 04:50 2h 31m 28s
llama : simplify Mamba with advanced batch splits (#8526)
Publish Docker image #14387: Commit a1631e5 pushed by compilade
August 21, 2024 21:58 2h 48m 6s master
August 21, 2024 21:58 2h 48m 6s
server : support reading arguments from environment variables (#9105)
Publish Docker image #14386: Commit fc54ef0 pushed by ngxson
August 21, 2024 09:04 5h 46m 37s master
August 21, 2024 09:04 5h 46m 37s
llama : support for falcon-mamba architecture (#9074)
Publish Docker image #14385: Commit b40eb84 pushed by ggerganov
August 21, 2024 08:06 4h 53m 43s master
August 21, 2024 08:06 4h 53m 43s
llava : zero-initialize clip_ctx structure fields with aggregate init…
Publish Docker image #14384: Commit f63f603 pushed by fairydreaming
August 21, 2024 07:45 3h 11m 52s master
August 21, 2024 07:45 3h 11m 52s
llama : std::move llm_bigram_bpe from work_queue (#9062)
Publish Docker image #14383: Commit 8455340 pushed by ggerganov
August 21, 2024 07:33 2h 49m 23s master
August 21, 2024 07:33 2h 49m 23s
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the L…
Publish Docker image #14382: Commit 2f3c146 pushed by 0cc4m
August 20, 2024 19:00 2h 38m 15s master
August 20, 2024 19:00 2h 38m 15s
[SYCL] fallback mmvq (#9088)
Publish Docker image #14381: Commit 50addec pushed by NeoZhangJianyu
August 20, 2024 15:50 2h 32m 15s master
August 20, 2024 15:50 2h 32m 15s
[SYCL] Fix SYCL im2col and convert Overflow with Large Dims (#9052)
Publish Docker image #14380: Commit 4f8d19f pushed by NeoZhangJianyu
August 20, 2024 15:06 2h 39m 39s master
August 20, 2024 15:06 2h 39m 39s