Skip to content

Actions: ggml-org/llama.cpp

Actions

Python check requirements.txt

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-check-requirements.yml
2,102 workflow runs
2,102 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Llama-3_1-Nemotron-Ultra-253B-v1 support Python check requirements.txt #2827: Pull request #12843 synchronize by ymcki
1h 23m 2s ymcki:master
ymcki:master
1h 23m 2s
convert : Llama4 RoPE fix (#12889) Python check requirements.txt #2826: Commit ec6c09d pushed by ngxson
30m 37s master
master
30m 37s
Llama4 RoPE fix Python check requirements.txt #2825: Pull request #12889 opened by danielhanchen
3m 40s patch-2
patch-2
3m 40s
convert : proper tensor name mapping for llama4 (#12870) Python check requirements.txt #2824: Commit 5b1f13c pushed by ngxson
20m 40s master
master
20m 40s
glm4-4-0414 : add Glm4Model implementation for GLM-4-0414 Python check requirements.txt #2823: Pull request #12867 synchronize by zRzRzRzRzRzRzR
9m 32s zRzRzRzRzRzRzR:master
zRzRzRzRzRzRzR:master
9m 32s
Use cast_data and typed_data struct to deduplicate casting code Python check requirements.txt #2820: Commit 8398060 pushed by qnixsynapse
3m 15s sycl/fp16elewisesupport
sycl/fp16elewisesupport
3m 15s
convert : ability to lazy-load safetensors remotely without downloadi… Python check requirements.txt #2819: Commit 64eda5d pushed by ngxson
3m 5s master
master
3m 5s
glm4-4-0414 : add Glm4Model implementation for GLM-4-0414 Python check requirements.txt #2818: Pull request #12867 synchronize by zRzRzRzRzRzRzR
2m 53s zRzRzRzRzRzRzR:master
zRzRzRzRzRzRzR:master
2m 53s
convert : proper tensor name mapping for llama4 Python check requirements.txt #2815: Pull request #12870 opened by ngxson
9m 56s ngxson:xsn/llama4_mapping
ngxson:xsn/llama4_mapping
9m 56s
glm4-4-0414 : add Glm4Model implementation for GLM-4-0414 Python check requirements.txt #2812: Pull request #12867 opened by zRzRzRzRzRzRzR
5m 41s zRzRzRzRzRzRzR:master
zRzRzRzRzRzRzR:master
5m 41s
convert : ability to lazy-load safetensors remotely without downloading to disk Python check requirements.txt #2811: Pull request #12820 synchronize by ngxson
14m 25s ngxson:xsn/lazy_remote_tensor
ngxson:xsn/lazy_remote_tensor
14m 25s
Llama-3_1-Nemotron-Ultra-253B-v1 support Python check requirements.txt #2810: Pull request #12843 synchronize by ymcki
3m 5s ymcki:master
ymcki:master
3m 5s
Llama-3_1-Nemotron-Ultra-253B-v1 support Python check requirements.txt #2809: Pull request #12843 synchronize by ymcki
30s ymcki:master
ymcki:master
30s
convert : ability to lazy-load safetensors remotely without downloading to disk Python check requirements.txt #2808: Pull request #12820 synchronize by ngxson
2m 48s ngxson:xsn/lazy_remote_tensor
ngxson:xsn/lazy_remote_tensor
2m 48s
llama : Support Qwen3 and Qwen3MoE (#12828) Python check requirements.txt #2807: Commit d3bd719 pushed by ngxson
7m 33s master
master
7m 33s
Llama-3_1-Nemotron-Ultra-253B-v1 support Python check requirements.txt #2806: Pull request #12843 opened by ymcki
7m 41s ymcki:master
ymcki:master
7m 41s
DeepSeek V2/V3 MLA implementation Python check requirements.txt #2805: Pull request #12801 synchronize by jukofyork
5m 0s mla--ready-for-review
mla--ready-for-review
5m 0s
Use static cast and remove unneeded castings Python check requirements.txt #2804: Commit fc8d0a6 pushed by qnixsynapse
3m 9s sycl/fp16elewisesupport
sycl/fp16elewisesupport
3m 9s
convert : write tensors in parallel Python check requirements.txt #2803: Pull request #12837 synchronize by compilade
2m 52s compilade/parallel-convert
compilade/parallel-convert
2m 52s
convert : write tensors in parallel Python check requirements.txt #2802: Pull request #12837 opened by compilade
2m 53s compilade/parallel-convert
compilade/parallel-convert
2m 53s
convert : write tensors in parallel Python check requirements.txt #2801: Commit 06e1d31 pushed by compilade
3m 12s compilade/parallel-convert
compilade/parallel-convert
3m 12s
convert : write tensors in parallel Python check requirements.txt #2800: Commit c0b5327 pushed by compilade
3m 31s compilade/parallel-convert
compilade/parallel-convert
3m 31s
Support Qwen3 and Qwen3MoE Python check requirements.txt #2799: Pull request #12828 synchronize by bozheng-hit
2m 47s bozheng-hit:qwen3
bozheng-hit:qwen3
2m 47s
convert : ability to lazy-load safetensors remotely without downloading to disk Python check requirements.txt #2798: Pull request #12820 synchronize by ngxson
4m 10s ngxson:xsn/lazy_remote_tensor
ngxson:xsn/lazy_remote_tensor
4m 10s
convert : ability to lazy-load safetensors remotely without downloading to disk Python check requirements.txt #2797: Pull request #12820 synchronize by ngxson
4m 34s ngxson:xsn/lazy_remote_tensor
ngxson:xsn/lazy_remote_tensor
4m 34s
ProTip! You can narrow down the results and go further in time using created:<2025-04-08 or the other filters available.