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
733 workflow runs
733 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

wip lfm2 vision model Python Type-Check #728: Commit 955b18e pushed by ngxson
1m 43s xsn/lfm2_vl
xsn/lfm2_vl
1m 43s
mtmd : Fix MinicpmV model converter and clip to avoid using hardcode.… Python Type-Check #727: Commit cf9e564 pushed by ngxson
2m 3s master
master
2m 3s
convert : fix merge conflicts (#15229) Python Type-Check #726: Commit 50e81bd pushed by ngxson
1m 31s master
master
1m 31s
convert : improve Mistral models integration (#14737) Python Type-Check #725: Commit a3a7874 pushed by ngxson
2m 36s master
master
2m 36s
gguf-py : add Numpy MXFP4 de/quantization support (#15111) Python Type-Check #724: Commit e54d41b pushed by ngxson
1m 56s master
master
1m 56s
server-bench: external OAI servers, sqlite (#15179) Python Type-Check #723: Commit 4850b52 pushed by ngxson
1m 57s master
master
1m 57s
convert : support non-mxfp4 HF model (#15153) Python Type-Check #722: Commit 50aa938 pushed by ngxson
1m 45s master
master
1m 45s
disable debug check Python Type-Check #721: Commit bbe8c21 pushed by ngxson
1m 48s xsn/gptoss_non_mxfp4_conversion
xsn/gptoss_non_mxfp4_conversion
1m 48s
llama : Support intern-s1 (#14875) Python Type-Check #720: Commit 99acbc9 pushed by ngxson
1m 55s master
master
1m 55s
convert : support non-mxfp4 HF model Python Type-Check #719: Commit b1cbcdd pushed by ngxson
1m 35s xsn/gptoss_non_mxfp4_conversion
xsn/gptoss_non_mxfp4_conversion
1m 35s
scripts: fix crash when --tool is not set (#15133) Python Type-Check #718: Commit 20638e4 pushed by ngxson
1m 38s master
master
1m 38s
requirements : fix PyTorch uint64 compatibility (#15134) Python Type-Check #717: Commit 36d3f00 pushed by ngxson
2m 28s master
master
2m 28s
llama : add gpt-oss (#15091) Python Type-Check #716: Commit fd1234c pushed by ngxson
5m 13s master
master
5m 13s
gguf-py : add --chat-template-file to gguf_new_metadata (#15075) Python Type-Check #715: Commit e5bebe5 pushed by ngxson
2m 23s master
master
2m 23s
model: support GLM 4.5 family of models (#14939) Python Type-Check #714: Commit ef0144c pushed by ngxson
2m 4s master
master
2m 4s
vocab : JetBrains Mellum pre-tokenizer (#15045) Python Type-Check #713: Commit 97366dc pushed by ngxson
1m 36s master
master
1m 36s
model : add text-only support for Kimi-VL (and find special tokens in… Python Type-Check #712: Commit 83bc2f2 pushed by ngxson
1m 33s master
master
1m 33s
ci : check that pre-tokenizer hashes are up-to-date (#15032) Python Type-Check #711: Commit 2bf3fbf pushed by ngxson
2m 8s master
master
2m 8s
convert : fix Qwen3-Embedding pre-tokenizer hash (#15030) Python Type-Check #710: Commit 711d5e6 pushed by ngxson
1m 41s master
master
1m 41s
vulkan: coopmat2 mul_mat optimizations (#14934) Python Type-Check #709: Commit 4cb208c pushed by ngxson
1m 33s master
master
1m 33s
model : support Qwen3-Embedding (#15023) Python Type-Check #708: Commit 339bd02 pushed by ngxson
1m 44s master
master
1m 44s
model : add hunyuan dense (#14878) Python Type-Check #707: Commit 0f5ccd6 pushed by ngxson
4m 56s master
master
4m 56s
compare-commits.sh: support both llama-bench and test-backend-ops (#1… Python Type-Check #706: Commit 484b209 pushed by ngxson
2m 3s master
master
2m 3s
mtmd : support MiniCPM-V 4.0 (#14983) Python Type-Check #705: Commit 952a47f pushed by ngxson
1m 37s master
master
1m 37s
MODEL_TENSOR.SSM_DT_NORM has defined twice (#14991) Python Type-Check #704: Commit 36e5fe7 pushed by ngxson
2m 18s master
master
2m 18s