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
2,500+ workflow runs
2,500+ 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
Merge branch 'master' into xsn/server_schema Python check requirements.txt #6754: Commit 695d643 pushed by ngxson
49m 4s xsn/server_schema
xsn/server_schema
49m 4s
remove duplicated init calls Python check requirements.txt #6753: Commit d1b5a68 pushed by 0cc4m
20m 32s 0cc4m/server-memory-limit
0cc4m/server-memory-limit
20m 32s
tests: add backend copy test Python check requirements.txt #6752: Commit e804ed3 pushed by 0cc4m
4m 42s 0cc4m/test-backend-copy
0cc4m/test-backend-copy
4m 42s
ci(snapdragon): add Windows on ARM64 build and test via Qualcomm Device Cloud Python check requirements.txt #6751: Pull request #24700 synchronize by zhiyuan8
3m 44s qualcomm:feature/windows-support
qualcomm:feature/windows-support
3m 44s
common/log: remove queue expansion logic Python check requirements.txt #6750: Commit e2427f6 pushed by max-krasnyansky
3m 49s maxk/logging-max-capacity
maxk/logging-max-capacity
3m 49s
ci(snapdragon): add Windows on ARM64 build and test via Qualcomm Device Cloud Python check requirements.txt #6749: Pull request #24700 synchronize by zhiyuan8
Action required qualcomm:feature/windows-support
qualcomm:feature/windows-support
Action required
ci(snapdragon): add Windows on ARM64 build and test via Qualcomm Device Cloud Python check requirements.txt #6748: Pull request #24700 opened by zhiyuan8
Action required qualcomm:feature/windows-support
qualcomm:feature/windows-support
Action required
cont : fix cur_buf_size init after flushing a buffer Python check requirements.txt #6747: Commit 7c7be0f pushed by ggerganov
1h 8m 52s gg/ggml-alloc-refactor-meta
gg/ggml-alloc-refactor-meta
1h 8m 52s
convert : fix lora base model arch retrieval (#24621) Python check requirements.txt #6746: Commit dd4623a pushed by ngxson
3m 20s master
master
3m 20s
convert : reorder V heads for LoraTorchTensor Python check requirements.txt #6744: Pull request #24627 opened by javierdejesusda
Action required javierdejesusda:fix/21125-lora-qwen35-vhead-reshape
javierdejesusda:fix/21125-lora-qwen35-vhead-reshape
Action required
fix(convert): avoid eager KeyError when hparams lacks top-level architectures Python check requirements.txt #6743: Pull request #24614 reopened by franitel
Action required franitel:fix-lora-convert-keyerror
franitel:fix-lora-convert-keyerror
Action required
common: update logging to enforce max_capacity and optimize queue res… Python check requirements.txt #6742: Commit 81acb32 pushed by max-krasnyansky
18m 40s maxk/logging-max-capacity
maxk/logging-max-capacity
18m 40s
convert : fix lora base model arch retrieval Python check requirements.txt #6741: Pull request #24621 opened by CISC
3m 33s cisc/convert-lora-get-model-architecture
cisc/convert-lora-get-model-architecture
3m 33s
fix lora base model arch retrieval Python check requirements.txt #6740: Commit 40f0f2b pushed by CISC
3m 28s cisc/convert-lora-get-model-architecture
cisc/convert-lora-get-model-architecture
3m 28s
Add arch support for cohere2-MoE (#24260) Python check requirements.txt #6737: Commit 4988f6e pushed by pwilkin
7m 32s master
master
7m 32s
common: update logging to enforce max_capacity and optimize queue res… Python check requirements.txt #6736: Commit 5448518 pushed by max-krasnyansky
13m 58s maxk/logging-max-capacity
maxk/logging-max-capacity
13m 58s
Reduce RSS during BF16 GGUF export Python check requirements.txt #6735: Pull request #24548 opened by i386
Action required Mesh-LLM:feat/reduce-bf16-convert-memory
Mesh-LLM:feat/reduce-bf16-convert-memory
Action required
Add arch support for cohere2-MoE Python check requirements.txt #6734: Pull request #24260 synchronize by michaelw9999
37m 29s michaelw9999:cohere2-moe
michaelw9999:cohere2-moe
37m 29s
spec: add EAGLE3 speculative decoding support (#18039) Python check requirements.txt #6733: Commit 88a3927 pushed by ggerganov
35m 18s master
master
35m 18s
remove unnecessary host write pipeline barriers Python check requirements.txt #6732: Commit d998fbf pushed by 0cc4m
54m 21s 0cc4m/vulkan-host-pipeline-barriers
0cc4m/vulkan-host-pipeline-barriers
54m 21s
[Speculative decoding] feat: add EAGLE3 speculative decoding support Python check requirements.txt #6729: Pull request #18039 synchronize by ruixiang63
6m 45s ruixiang63:eagle3-adapt-new-arch
ruixiang63:eagle3-adapt-new-arch
6m 45s
[Speculative decoding] feat: add EAGLE3 speculative decoding support Python check requirements.txt #6728: Pull request #18039 synchronize by ggerganov
3m 48s ruixiang63:eagle3-adapt-new-arch
ruixiang63:eagle3-adapt-new-arch
3m 48s
[Speculative decoding] feat: add EAGLE3 speculative decoding support Python check requirements.txt #6726: Pull request #18039 synchronize by ggerganov
3m 38s ruixiang63:eagle3-adapt-new-arch
ruixiang63:eagle3-adapt-new-arch
3m 38s
[Speculative decoding] feat: add EAGLE3 speculative decoding support Python check requirements.txt #6722: Pull request #18039 synchronize by ggerganov
25m 8s ruixiang63:eagle3-adapt-new-arch
ruixiang63:eagle3-adapt-new-arch
25m 8s
Add arch support for cohere2-MoE Python check requirements.txt #6718: Pull request #24260 synchronize by michaelw9999
Action required michaelw9999:cohere2-moe
michaelw9999:cohere2-moe
Action required