Skip to content

Actions: ggerganov/llama.cpp

Pull Request Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
4,069 workflow run results
4,069 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add newline after chat example in llama-server
Pull Request Labeler #4069: Pull request #9616 opened by StrangeBytesDev
September 23, 2024 23:40 14s
September 23, 2024 23:40 14s
threads: fix msvc build without openmp
Pull Request Labeler #4068: Pull request #9615 opened by max-krasnyansky
September 23, 2024 22:30 15s
September 23, 2024 22:30 15s
IBM Granite MoE Architecture
Pull Request Labeler #4067: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 20:00 19s
September 23, 2024 20:00 19s
IBM Granite MoE Architecture
Pull Request Labeler #4066: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 19:56 14s
September 23, 2024 19:56 14s
IBM Granite MoE Architecture
Pull Request Labeler #4065: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 18:55 46s
September 23, 2024 18:55 46s
llama : add reranking support
Pull Request Labeler #4064: Pull request #9510 synchronize by ggerganov
September 23, 2024 17:20 21m 45s
September 23, 2024 17:20 21m 45s
IBM Granite MoE Architecture
Pull Request Labeler #4063: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 17:04 14m 55s
September 23, 2024 17:04 14m 55s
threads: improve ggml_barrier scaling with large number of threads
Pull Request Labeler #4062: Pull request #9598 synchronize by max-krasnyansky
September 23, 2024 16:33 23m 13s
September 23, 2024 16:33 23m 13s
server : add --no-context-shift option
Pull Request Labeler #4061: Pull request #9607 synchronize by ngxson
September 23, 2024 16:13 26m 51s
September 23, 2024 16:13 26m 51s
IBM Granite MoE Architecture
Pull Request Labeler #4060: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 15:32 42m 41s
September 23, 2024 15:32 42m 41s
merge main
Pull Request Labeler #4059: Pull request #9611 opened by Aliebc
September 23, 2024 15:18 40m 9s
September 23, 2024 15:18 40m 9s
log : add CONT level for continuing previous log entry
Pull Request Labeler #4058: Pull request #9610 opened by ggerganov
September 23, 2024 15:05 41m 4s
September 23, 2024 15:05 41m 4s
sampling : avoid expensive softmax during greedy sampling
Pull Request Labeler #4057: Pull request #9605 synchronize by ggerganov
September 23, 2024 14:18 1h 7m 45s
September 23, 2024 14:18 1h 7m 45s
IBM Granite MoE Architecture
Pull Request Labeler #4056: Pull request #9438 synchronize by gabe-l-hart
September 23, 2024 14:17 44m 12s
September 23, 2024 14:17 44m 12s
llama : keep track of all EOG tokens in the vocab
Pull Request Labeler #4055: Pull request #9609 opened by ggerganov
September 23, 2024 14:02 18s
September 23, 2024 14:02 18s
server : add --no-context-shift option
Pull Request Labeler #4054: Pull request #9607 synchronize by ngxson
September 23, 2024 13:20 17s
September 23, 2024 13:20 17s
Implementations for Q4_0_8_8 quantization based functions - AVX512 version of ggml_gemm_q4_0_8x8_q8_0
Pull Request Labeler #4053: Pull request #9532 synchronize by Srihari-mcw
September 23, 2024 12:49 14s
September 23, 2024 12:49 14s
server : add --no-context-shift option
Pull Request Labeler #4052: Pull request #9607 synchronize by ngxson
September 23, 2024 12:28 24s
September 23, 2024 12:28 24s
server : add --no-context-shift option
Pull Request Labeler #4051: Pull request #9607 synchronize by ngxson
September 23, 2024 12:27 22s
September 23, 2024 12:27 22s
server : add --no-context-shift option
Pull Request Labeler #4050: Pull request #9607 synchronize by ngxson
September 23, 2024 12:26 13s
September 23, 2024 12:26 13s
Update clip.cpp
Pull Request Labeler #4049: Pull request #9482 synchronize by Tejaakshaykumar
September 23, 2024 11:39 9m 25s
September 23, 2024 11:39 9m 25s
server : add --no-context-shift option
Pull Request Labeler #4048: Pull request #9607 opened by ngxson
September 23, 2024 11:37 19s
September 23, 2024 11:37 19s
Implementations for Q4_0_8_8 quantization based functions - AVX512 version of ggml_gemm_q4_0_8x8_q8_0
Pull Request Labeler #4047: Pull request #9532 synchronize by ggerganov
September 23, 2024 10:42 11m 15s
September 23, 2024 10:42 11m 15s
Implementations for Q4_0_8_8 quantization based functions - AVX512 version of ggml_gemm_q4_0_8x8_q8_0
Pull Request Labeler #4046: Pull request #9532 synchronize by Srihari-mcw
September 23, 2024 10:16 24m 41s
September 23, 2024 10:16 24m 41s
sampling : avoid expensive softmax during greedy sampling
Pull Request Labeler #4045: Pull request #9605 opened by ggerganov
September 23, 2024 09:49 40m 20s
September 23, 2024 09:49 40m 20s