Skip to content

Actions: taronaeo/llama.cpp-s390x

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
71 workflow runs
71 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
ggml-virtgpu : include missing mutex header (#22810) Check Pre-Tokenizer Hashes #71: Commit 2b2babd pushed by taronaeo
29m 13s master
master
29m 13s
fix: broken rebase with upstream/master Check Pre-Tokenizer Hashes #70: Commit 3ce3b6d pushed by taronaeo
1m 2s refactor/mmap-dio
refactor/mmap-dio
1m 2s
llama-bench: forgot one last deprecation message Check Pre-Tokenizer Hashes #69: Commit 4e19747 pushed by taronaeo
1m 4s refactor/mmap-dio
refactor/mmap-dio
1m 4s
llama-bench: bring back support for --mmap and --direct-io for now Check Pre-Tokenizer Hashes #68: Commit 88ca79d pushed by taronaeo
1m 14s refactor/mmap-dio
refactor/mmap-dio
1m 14s
server : fix logging of build + system info (#21460) Check Pre-Tokenizer Hashes #67: Commit 5d3a4a7 pushed by taronaeo
1m 11s fix/server-sampling-params
fix/server-sampling-params
1m 11s
ci: add git, git-lfs, wget, python3, pip3, python3-venv and ccache ch… Check Pre-Tokenizer Hashes #66: Commit 0d4180d pushed by taronaeo
1m 9s feat/ci-check-deps
feat/ci-check-deps
1m 9s
revert: rm llama-mmap.cpp debug lines Check Pre-Tokenizer Hashes #65: Commit e3ca2c4 pushed by taronaeo
1m 40s refactor/mmap-dio
refactor/mmap-dio
1m 40s
args: add newline Check Pre-Tokenizer Hashes #64: Commit a0a86cf pushed by taronaeo
1m 8s refactor/mmap-dio-copy
refactor/mmap-dio-copy
1m 8s
ci: add audit workflow Check Pre-Tokenizer Hashes #63: Commit 91d12fa pushed by taronaeo
12m 2s master
master
12m 2s
ci: add audit workflow Check Pre-Tokenizer Hashes #62: Commit 91d12fa pushed by taronaeo
59s feat/ci-self-hosted-audit
feat/ci-self-hosted-audit
59s
ggml-backend: re-enable graph reuse with pipeline parallelism (#20927) Check Pre-Tokenizer Hashes #61: Commit 3fc6f1a pushed by taronaeo
1m 2s master
master
1m 2s
issues: add openvino backends Check Pre-Tokenizer Hashes #60: Commit 7fcaba7 pushed by taronaeo
59s feat/openvino-issue-template
feat/openvino-issue-template
59s
args: refactor mlock/mmap/directio into load-mode Check Pre-Tokenizer Hashes #59: Commit 0438041 pushed by taronaeo
54s refactor/mmap-dio
refactor/mmap-dio
54s
codeowners : use teams (#20526) Check Pre-Tokenizer Hashes #58: Commit cf45437 pushed by taronaeo
1m 3s master
master
1m 3s
llama-bench: fix case where mmap and direct-io are turned on together Check Pre-Tokenizer Hashes #57: Commit a320bed pushed by taronaeo
1m 39s fix/bench-mmap-dio-flags
fix/bench-mmap-dio-flags
1m 39s
ggml: update comments for backends which have no memory to report Check Pre-Tokenizer Hashes #56: Commit 53c6d65 pushed by taronaeo
55s chore/rm-backend-memory-todos
chore/rm-backend-memory-todos
55s
ggml-cpu: initial optimisation test on q4_0 Check Pre-Tokenizer Hashes #55: Commit ef06ca3 pushed by taronaeo
1m 2s refactor/vec-mul-eo
refactor/vec-mul-eo
1m 2s
ggml-virtgpu: improve the reliability of the code (#19846) Check Pre-Tokenizer Hashes #54: Commit ffaafde pushed by taronaeo
53s feat/s390x-repack
feat/s390x-repack
53s
llama: make cpu backend visible to llama_params_fit Check Pre-Tokenizer Hashes #53: Commit 807ecd9 pushed by taronaeo
1m 50s fix/fit-host-memory
fix/fit-host-memory
1m 50s
test Check Pre-Tokenizer Hashes #52: Commit 48c479e pushed by taronaeo
1m 13s test
test
1m 13s
llama: default to 2048 context size for cpu-only build Check Pre-Tokenizer Hashes #51: Commit a370cbb pushed by taronaeo
58s fix/fit-host-memory
fix/fit-host-memory
58s
ggml-cpu: optimize ggml_vec_dot_bf16 for s390x (#19399) Check Pre-Tokenizer Hashes #50: Commit 184c694 pushed by taronaeo
1m 3s master
master
1m 3s
chore: initial comments breakdown Check Pre-Tokenizer Hashes #49: Commit 1d84642 pushed by taronaeo
53s fix/fit-host-memory
fix/fit-host-memory
53s
ggml-cpu: fix incorrect macro Check Pre-Tokenizer Hashes #48: Commit c72407f pushed by taronaeo
1m 4s feat/s390x-bf16
feat/s390x-bf16
1m 4s
Kimi-Linear support (backend agnostic + MLA KV cache) (#18755) Check Pre-Tokenizer Hashes #47: Commit 3688c4f pushed by taronaeo
59s master
master
59s