Skip to content

Actions: ochafik/llama.cpp

Actions

flake8 Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-lint.yml
46 workflow runs
46 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

support permuted, remove check s0/s10 (#19889) flake8 Lint #902: Commit 2943210 pushed by ochafik
41s master
master
41s
hexagon: fix typo in vtcm_needs_release (#19545) flake8 Lint #901: Commit 3bb7813 pushed by ochafik
49s master
master
49s
docker : add CUDA 13.1 image build (#18441) flake8 Lint #900: Commit 4849661 pushed by ochafik
13m 29s master
master
13m 29s
ggml-cuda: fix regex for arch list (#18371) flake8 Lint #899: Commit 85c40c9 pushed by ochafik
19s master
master
19s
webui: redesign MCP picker to match model selector style flake8 Lint #898: Commit 550e937 pushed by ochafik
17s master
master
17s
llama : Changing off_t to size_t for Windows (#18204) flake8 Lint #897: Commit f99ef53 pushed by ochafik
15s master
master
15s
preset: handle negated arg, reverse the meaning if needed (#18041) flake8 Lint #896: Commit 5239229 pushed by ochafik
19s master
master
19s
server: strip content-length header on proxy (#17734) flake8 Lint #895: Commit 9d02299 pushed by ochafik
16s master
master
16s
ggml webgpu: profiling, CI updates, reworking of command submission (… flake8 Lint #894: Commit 74b8fc1 pushed by ochafik
22s master
master
22s
test-opt: allow slight inprecision (#15503) flake8 Lint #893: Commit e92734d pushed by ochafik
19s master
master
19s
convert : support non-mxfp4 HF model (#15153) flake8 Lint #892: Commit 50aa938 pushed by ochafik
1m 24s master
master
1m 24s
llama : add gpt-oss (#15091) flake8 Lint #891: Commit fd1234c pushed by ochafik
17s master
master
17s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) flake8 Lint #890: Commit 711d5e6 pushed by ochafik
24s master
master
24s
parallel : increase the variability of the prompt lengths (#13927) flake8 Lint #889: Commit dd665cc pushed by ochafik
26s master
master
26s
llama : add support for jina-reranker-v2 (#13900) flake8 Lint #888: Commit e83ba3e pushed by ochafik
24s master
master
24s
server: fix format of streamed tool call deltas (diff name, fix id … flake8 Lint #887: Commit d74e94c pushed by ochafik
19s master
master
19s
server: fix regression on streamed non-chat completion w/ stops (#13785) flake8 Lint #886: Commit f13847c pushed by ochafik
29s master
master
29s
server: add --reasoning-budget 0 to disable thinking (incl. qwen3… flake8 Lint #885: Commit e121edc pushed by ochafik
23s master
master
23s
server: fix/test add_generation_prompt flake8 Lint #884: Commit 7cea29b pushed by ochafik
18s master
master
18s
server: streaming of tool calls and thoughts when --jinja is on (… flake8 Lint #883: Commit f5cd27b pushed by ochafik
20s master
master
20s
ci : enable winget package updates (#13734) flake8 Lint #882: Commit b775345 pushed by ochafik
26s master
master
26s
CANN: Support MUL_MAT_ID for q8_0 and q4_0 (#13705) flake8 Lint #881: Commit faaaff5 pushed by ochafik
31s master
master
31s
llguidance : official v0.7.20 release (no actual changes) [noci] (#13… flake8 Lint #880: Commit 3e0be1c pushed by ochafik
23s master
master
23s
gguf : use ggml log system (#13571) flake8 Lint #879: Commit c6a2c9e pushed by ochafik
27s master
master
27s
server : proper error handling for missing elements in messages array… flake8 Lint #878: Commit c753d7b pushed by ochafik
24s master
master
24s