Skip to content

Actions: ggerganov/llama.cpp

Actions

Benchmark

Actions

Loading...

Show workflow options

Create status badge

bench.yml
2,013 workflow runs
2,013 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
common : refactor cli arg parsing Benchmark #2019: Pull request #7675 synchronize by ggerganov
June 3, 2024 13:50 Queued
June 3, 2024 13:50 Queued
common : refactor cli arg parsing Benchmark #2018: Pull request #7675 synchronize by ggerganov
June 3, 2024 13:49 1m 6s
June 3, 2024 13:49 1m 6s
common : refactor cli arg parsing Benchmark #2017: Pull request #7675 synchronize by ggerganov
June 3, 2024 12:59 50m 22s
June 3, 2024 12:59 50m 22s
common : refactor cli arg parsing Benchmark #2016: Pull request #7675 synchronize by ggerganov
June 3, 2024 12:41 17m 52s
June 3, 2024 12:41 17m 52s
ggml: Support OpenMP for multi-thread processing Benchmark #2015: Pull request #7606 synchronize by slaren
June 3, 2024 12:18 Queued
June 3, 2024 12:18 Queued
Poro-34B-chat tokenizer support Benchmark #2014: Pull request #7713 opened by ezosa
June 3, 2024 12:10 7m 45s
June 3, 2024 12:10 7m 45s
llama : offload to RPC in addition to other backends Benchmark #2013: Pull request #7640 synchronize by rgerganov
June 3, 2024 11:59 Queued
June 3, 2024 11:59 Queued
Vulkan Mixture of Experts (MoE) support (#7628) Benchmark #2012: Commit 3d7ebf6 pushed by 0cc4m
June 3, 2024 08:59 Queued master
master
June 3, 2024 08:59 Queued
[SYCL] remove global variables Benchmark #2011: Pull request #7710 opened by airMeng
June 3, 2024 08:07 Queued
June 3, 2024 08:07 Queued
llama : MiniCPM support tied embeddings (#7664) Benchmark #2010: Commit 6f28a33 pushed by ggerganov
June 3, 2024 07:49 Queued master
master
June 3, 2024 07:49 Queued
llama : offload to RPC in addition to other backends Benchmark #2009: Pull request #7640 synchronize by rgerganov
June 3, 2024 07:20 4h 39m 38s
June 3, 2024 07:20 4h 39m 38s
llama : offload to RPC in addition to other backends Benchmark #2008: Pull request #7640 synchronize by rgerganov
June 3, 2024 06:46 33m 30s
June 3, 2024 06:46 33m 30s
MiniCPM Support lm_head Benchmark #2007: Pull request #7664 synchronize by zkh2016
June 3, 2024 05:47 Queued
June 3, 2024 05:47 Queued
llama : avoid double token-to-piece cache (#7654) Benchmark #2006: Commit 549279d pushed by ggerganov
June 3, 2024 05:34 Queued master
master
June 3, 2024 05:34 Queued
llama : support Jamba hybrid Transformer-Mamba models Benchmark #2005: Pull request #7531 synchronize by compilade
June 3, 2024 04:13 Queued
June 3, 2024 04:13 Queued
Add Intel Advanced Matrix Extensions (AMX) support to ggml Benchmark #2004: Pull request #7707 opened by mingfeima
June 3, 2024 02:29 Queued
June 3, 2024 02:29 Queued
Benchmark Benchmark #2003: Scheduled
June 3, 2024 02:20 Queued master
master
June 3, 2024 02:20 Queued
PHI3-vision gguf conversion Benchmark #2002: Pull request #7705 opened by farris
June 3, 2024 01:22 Queued
June 3, 2024 01:22 Queued
Per token attributes Benchmark #2001: Pull request #7685 synchronize by jaime-m-p
June 2, 2024 23:49 Queued
June 2, 2024 23:49 Queued
Per token attributes Benchmark #2000: Pull request #7685 synchronize by jaime-m-p
June 2, 2024 22:52 57m 3s
June 2, 2024 22:52 57m 3s
Automate vocab support and model conversion Benchmark #1999: Pull request #7379 synchronize by teleprint-me
June 2, 2024 20:29 Queued
June 2, 2024 20:29 Queued
fix: don't add space after special tokens in SPM Benchmark #1998: Pull request #7697 synchronize by giladgd
June 2, 2024 19:44 Queued
June 2, 2024 19:44 Queued
ggml : unify rope norm/neox Benchmark #1997: Pull request #7634 synchronize by ggerganov
June 2, 2024 17:09 20h 36m 32s
June 2, 2024 17:09 20h 36m 32s
fix: don't add space after special tokens in SPM Benchmark #1996: Pull request #7697 opened by giladgd
June 2, 2024 16:59 2h 45m 26s
June 2, 2024 16:59 2h 45m 26s
ggml : unify rope norm/neox Benchmark #1995: Pull request #7634 synchronize by ggerganov
June 2, 2024 16:59 10m 14s
June 2, 2024 16:59 10m 14s