Skip to content

Actions: ngxson/llama.cpp

Actions

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-type-check.yml
738 workflow runs
738 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

convert : add Llama4ForCausalLM (#16042) Python Type-Check #778: Commit 8f8f227 pushed by ngxson
2m 12s master
master
2m 12s
model : add OLMo3 support (#16015) Python Type-Check #777: Commit 85286f3 pushed by ngxson
2m 18s master
master
2m 18s
half working version Python Type-Check #776: Commit c540db6 pushed by ngxson
2m 10s xsn/llama4causalfix
xsn/llama4causalfix
2m 10s
convert : add Llama4ForCausalLM Python Type-Check #775: Commit 66fe9ff pushed by ngxson
2m 51s xsn/llama4causalfix
xsn/llama4causalfix
2m 51s
convert : add Llama4ForCausalLM Python Type-Check #774: Commit bba0e61 pushed by ngxson
1m 48s xsn/llama4causal
xsn/llama4causal
1m 48s
Add LLaDA-7b-MoE diffusion model (#16003) Python Type-Check #773: Commit 6d75883 pushed by ngxson
6m 26s master
master
6m 26s
model : add grok-2 support (#15539) Python Type-Check #772: Commit b8e09f0 pushed by ngxson
3m 54s master
master
3m 54s
llama : support T5 models with unequal number of encoder-decoder laye… Python Type-Check #771: Commit 4f65885 pushed by ngxson
2m 33s master
master
2m 33s
CUDA: Add mul_mat_id support for the mmf kernel (#15767) Python Type-Check #770: Commit a972fae pushed by ngxson
2m 24s master
master
2m 24s
requirements : update transformers/torch for Embedding Gemma (#15828) Python Type-Check #769: Commit 70cd37d pushed by ngxson
2m 0s master
master
2m 0s
json : support enum values within allOf (#15830) Python Type-Check #768: Commit 7057faf pushed by ngxson
1m 38s master
master
1m 38s
CUDA: generate_cu_files.py - add missing mxfp4 (#15880) Python Type-Check #767: Commit 0a16bf5 pushed by ngxson
1m 52s master
master
1m 52s
convert : force setting sliding_window from original config (#15867) Python Type-Check #766: Commit 233d773 pushed by ngxson
1m 40s master
master
1m 40s
server : speed up tests (#15836) Python Type-Check #765: Commit 3c3635d pushed by ngxson
1m 53s master
master
1m 53s
server : implement prompt processing progress report in stream mode (… Python Type-Check #764: Commit 61bdfd5 pushed by ngxson
2m 24s master
master
2m 24s
aLoRA Support (#15327) Python Type-Check #763: Commit fd62188 pushed by ngxson
1m 40s master
master
1m 40s
scripts : add Jinja tester PySide6 simple app (#15756) Python Type-Check #762: Commit 9e2b1e8 pushed by ngxson
2m 6s master
master
2m 6s
llama : add support for EmbeddingGemma 300m (#15798) Python Type-Check #761: Commit fb15d64 pushed by ngxson
2m 14s master
master
2m 14s
server: add exceed_context_size_error type (#15780) Python Type-Check #760: Commit a68d914 pushed by ngxson
3m 45s master
master
3m 45s
change error code to 400 Python Type-Check #759: Commit 6aaf4f3 pushed by ngxson
1m 49s xsn/exceed_context_size_error
xsn/exceed_context_size_error
1m 49s
server: add exceed_context_size_error type Python Type-Check #758: Commit 6051d69 pushed by ngxson
2m 18s xsn/exceed_context_size_error
xsn/exceed_context_size_error
2m 18s
model-conversion : fix pyright errors (#15770) Python Type-Check #757: Commit 407c237 pushed by ngxson
1m 50s master
master
1m 50s
convert : remove redundant code (#15708) Python Type-Check #756: Commit 4b20d8b pushed by ngxson
1m 56s master
master
1m 56s
server : enable /slots by default and make it secure (#15630) Python Type-Check #755: Commit 0d161f0 pushed by ngxson
5m 41s master
master
5m 41s
llama: use FA + max. GPU layers by default (#15434) Python Type-Check #754: Commit e81b8e4 pushed by ngxson
8m 24s master
master
8m 24s