Skip to content

Actions: ggerganov/llama.cpp

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
9,991 workflow runs
9,991 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: Throttle the number of shader compiles during the build step.…
Publish Docker image #14696: Commit 54ef9cf pushed by 0cc4m
November 11, 2024 17:13 31m 41s master
November 11, 2024 17:13 31m 41s
metal : more precise Q*K in FA vec kernel (#10247)
Publish Docker image #14695: Commit b0cefea pushed by ggerganov
November 11, 2024 06:39 1h 21m 40s master
November 11, 2024 06:39 1h 21m 40s
server : enable KV cache defrag by default (#10233)
Publish Docker image #14694: Commit b141e5f pushed by ggerganov
November 11, 2024 06:38 32m 50s master
November 11, 2024 06:38 32m 50s
vulkan: Fix newly added tests for permuted mul_mat and 1D im2col (#10…
Publish Docker image #14693: Commit 160687b pushed by 0cc4m
November 10, 2024 11:37 30m 12s master
November 10, 2024 11:37 30m 12s
metal : reorder write loop in mul mat kernel + style (#10231)
Publish Docker image #14692: Commit 6423c65 pushed by ggerganov
November 9, 2024 09:53 3h 8m 42s master
November 9, 2024 09:53 3h 8m 42s
metal : fix build and some more comments (#10229)
Publish Docker image #14691: Commit 39a334a pushed by ggerganov
November 9, 2024 09:53 2h 39m 43s master
November 9, 2024 09:53 2h 39m 43s
metal : fix F32 accumulation in FA vec kernel (#10232)
Publish Docker image #14690: Commit bb38cdd pushed by ggerganov
November 9, 2024 09:52 1h 50m 16s master
November 9, 2024 09:52 1h 50m 16s
llama : fix Qwen model type strings
Publish Docker image #14689: Commit f018acb pushed by ggerganov
November 9, 2024 09:26 1h 33m 34s master
November 9, 2024 09:26 1h 33m 34s
metal : hide debug messages from normal log
Publish Docker image #14688: Commit 46323fa pushed by ggerganov
November 9, 2024 09:22 55m 16s master
November 9, 2024 09:22 55m 16s
ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL oper…
Publish Docker image #14687: Commit 5b359bb pushed by JohannesGaessler
November 9, 2024 07:35 1h 0m 52s master
November 9, 2024 07:35 1h 0m 52s
ggml : optimize llamafile cpu matrix multiplication for ppc64le (#10156)
Publish Docker image #14686: Commit e892134 pushed by ggerganov
November 9, 2024 07:17 30m 56s master
November 9, 2024 07:17 30m 56s
metal : opt-in compile flag for BF16 (#10218)
Publish Docker image #14685: Commit ec450d3 pushed by ggerganov
November 8, 2024 19:59 31m 25s master
November 8, 2024 19:59 31m 25s
metal : improve clarity (minor) (#10171)
Publish Docker image #14684: Commit 695ad75 pushed by ggerganov
November 8, 2024 16:38 34m 6s master
November 8, 2024 16:38 34m 6s
swift : exclude ggml-metal-embed.metal (#10211)
Publish Docker image #14683: Commit d05b312 pushed by ggerganov
November 8, 2024 09:34 1h 24m 16s master
November 8, 2024 09:34 1h 24m 16s
server : revamp chat UI with vuejs and daisyui (#10175)
Publish Docker image #14682: Commit a71d81c pushed by ngxson
November 7, 2024 21:31 31m 0s master
November 7, 2024 21:31 31m 0s
ggml : add ggml-cpu.h to the public headers (#10204)
Publish Docker image #14681: Commit 97404c4 pushed by slaren
November 7, 2024 17:16 1h 6m 28s master
November 7, 2024 17:16 1h 6m 28s
DRY: Fixes clone functionality (#10192)
Publish Docker image #14680: Commit 5107e8c pushed by slaren
November 7, 2024 15:20 45m 49s master
November 7, 2024 15:20 45m 49s
fix q4_0_8_8 format for corrupted tokens issue (#10198)
Publish Docker image #14679: Commit 2319126 pushed by slaren
November 7, 2024 08:02 31m 13s master
November 7, 2024 08:02 31m 13s
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acc…
Publish Docker image #14678: Commit 3bcd40b pushed by airMeng
November 7, 2024 07:19 45m 8s master
November 7, 2024 07:19 45m 8s
server : remove hack for extra parallel slot (#10187)
Publish Docker image #14677: Commit b11f9ba pushed by ggerganov
November 6, 2024 11:29 1h 13m 24s master
November 6, 2024 11:29 1h 13m 24s
metal : fix from ptr buffer name (#10189)
Publish Docker image #14676: Commit 94d8cb8 pushed by slaren
November 6, 2024 11:10 1h 13m 48s master
November 6, 2024 11:10 1h 13m 48s
ggml : adjust is_first_call init value (#10193)
Publish Docker image #14675: Commit 1dc04b2 pushed by ggerganov
November 6, 2024 09:20 33m 8s master
November 6, 2024 09:20 33m 8s
llama : add <|tool_call|> formatting to Granite template (#10177)
Publish Docker image #14674: Commit b8deef0 pushed by ggerganov
November 5, 2024 12:23 46m 35s master
November 5, 2024 12:23 46m 35s
ggml : fix arch check in bf16_to_fp32 (#10164)
Publish Docker image #14673: Commit a9e8a9a pushed by slaren
November 4, 2024 22:17 1h 35m 9s master
November 4, 2024 22:17 1h 35m 9s
Q6_K AVX improvements (#10118)
Publish Docker image #14672: Commit 3407364 pushed by slaren
November 4, 2024 22:06 1h 3m 30s master
November 4, 2024 22:06 1h 3m 30s