Skip to content

Actions: ngxson/llama.cpp

Actions

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
118 workflow run results
118 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

mtgpu: enable VMM (#9597) Publish Docker image #346: Commit 7691654 pushed by ngxson
32m 8s master
master
32m 8s
ci : fix docker build number and tag name (#9638) Publish Docker image #345: Commit ea9c32b pushed by ngxson
34m 27s master
master
34m 27s
ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (#9217) Publish Docker image #344: Commit 1e43630 pushed by ngxson
1h 3m 49s master
master
1h 3m 49s
server : add more env vars, improve gen-docs (#9635) Publish Docker image #343: Commit afbbfaa pushed by ngxson
57m 14s master
master
57m 14s
llama : add IBM Granite MoE architecture (#9438) Publish Docker image #342: Commit 3d6bf69 pushed by ngxson
50m 30s master
master
50m 30s
cann: fix crash when llama-bench is running on multiple cann devices … Publish Docker image #341: Commit 904837e pushed by ngxson
30m 13s master
master
30m 13s
ggml : add AVX512DQ requirement for AVX512 builds (#9622) Publish Docker image #340: Commit 70392f1 pushed by ngxson
33m 33s master
master
33m 33s
llama : keep track of all EOG tokens in the vocab (#9609) Publish Docker image #339: Commit 31ac583 pushed by ngxson
32m 6s master
master
32m 6s
server : add newline after chat example (#9616) Publish Docker image #338: Commit 0aa1501 pushed by ngxson
30m 31s master
master
30m 31s
threads: fix msvc build without openmp (#9615) Publish Docker image #337: Commit c087b6f pushed by ngxson
30m 4s master
master
30m 4s
cuda: add q8_0->f32 cpy operation (#9571) Publish Docker image #336: Commit 116efee pushed by ngxson
34m 17s master
master
34m 17s
server : add --no-context-shift option (#9607) Publish Docker image #335: Commit 0b3bf96 pushed by ngxson
31m 1s master
master
31m 1s
threads: improve ggml_barrier scaling with large number of threads (#… Publish Docker image #334: Commit f0c7b5e pushed by ngxson
30m 11s master
master
30m 11s
ggml : AVX512 gemm for Q4_0_8_8 (#9532) Publish Docker image #333: Commit 1e7b929 pushed by ngxson
33m 7s master
master
33m 7s
perplexity : remove extra new lines after chunks (#9596) Publish Docker image #332: Commit 37f8c7b pushed by ngxson
33m 25s master
master
33m 25s
Revert "[SYCL] fallback mmvq (#9088)" (#9579) Publish Docker image #331: Commit e62e978 pushed by ngxson
31m 26s master
master
31m 26s
musa: enable building fat binaries, enable unified memory, and disabl… Publish Docker image #330: Commit c35e586 pushed by ngxson
33m 11s master
master
33m 11s
Fix merge error in #9454 (#9589) Publish Docker image #329: Commit 912c331 pushed by ngxson
30m 57s master
master
30m 57s
CUDA: enable Gemma FA for HIP/Pascal (#9581) Publish Docker image #328: Commit a5b57b0 pushed by ngxson
33m 9s master
master
33m 9s
llama: remove redundant loop when constructing ubatch (#9574) Publish Docker image #327: Commit ecd5d6b pushed by ngxson
32m 31s master
master
32m 31s
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG … Publish Docker image #326: Commit d09770c pushed by ngxson
30m 52s master
master
30m 52s
Update CUDA graph on scale change plus clear nodes/params (#9550) Publish Docker image #325: Commit 41f4778 pushed by ngxson
35m 12s master
master
35m 12s
quantize : improve type name parsing (#9570) Publish Docker image #324: Commit 6335114 pushed by ngxson
30m 19s master
master
30m 19s
ggml : fix builds (#0) Publish Docker image #323: Commit d13edb1 pushed by ngxson
33m 30s master
master
33m 30s
CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562) Publish Docker image #322: Commit 5cb12f6 pushed by ngxson
37m 7s master
master
37m 7s