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
737 workflow runs
737 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix tests Python Type-Check #99: Commit 3bea2e6 pushed by ngxson
1m 13s xsn/server_explicit_access
xsn/server_explicit_access
1m 13s
update server docs Python Type-Check #98: Commit 7fee203 pushed by ngxson
1m 9s xsn/server_explicit_access
xsn/server_explicit_access
1m 9s
wip Python Type-Check #97: Commit a88c0d5 pushed by ngxson
1m 21s xsn/vision
xsn/vision
1m 21s
convert : handle tokenizer merges format from transformers 4.45 (#9696) Python Type-Check #96: Commit e3c355b pushed by ngxson
1m 29s master
master
1m 29s
add more kv metadata Python Type-Check #95: Commit c2ec885 pushed by ngxson
1m 25s xsn/vision
xsn/vision
1m 25s
simple example works Python Type-Check #94: Commit 6089b0a pushed by ngxson
1m 27s xsn/vision
xsn/vision
1m 27s
convert : refactor rope_freqs generation (#9396) Python Type-Check #93: Commit 1927378 pushed by ngxson
1m 12s master
master
1m 12s
Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS (#9… Python Type-Check #92: Commit 6f1d9d7 pushed by ngxson
1m 10s master
master
1m 10s
py : update transfomers version (#9694) Python Type-Check #91: Commit 08a43d0 pushed by ngxson
1m 34s master
master
1m 34s
img pre processing Python Type-Check #90: Commit 6854ad4 pushed by ngxson
1m 22s xsn/vision
xsn/vision
1m 22s
model is loadable Python Type-Check #89: Commit a75c5c4 pushed by ngxson
1m 29s xsn/vision
xsn/vision
1m 29s
add llava to conversion Python Type-Check #88: Commit cd806a7 pushed by ngxson
1m 10s xsn/vision
xsn/vision
1m 10s
common : ensure llama_batch size does not exceed max size (#9668) Python Type-Check #87: Commit faac0ba pushed by ngxson
1m 16s master
master
1m 16s
test-backend-ops : use flops for some performance tests (#9657) Python Type-Check #86: Commit 1b2f992 pushed by ngxson
5m 23s master
master
5m 23s
llama : add IBM Granite MoE architecture (#9438) Python Type-Check #85: Commit 3d6bf69 pushed by ngxson
1m 12s master
master
1m 12s
server : add --no-context-shift option (#9607) Python Type-Check #84: Commit 0b3bf96 pushed by ngxson
1m 28s master
master
1m 28s
scripts : verify py deps at the start of compare (#9520) Python Type-Check #82: Commit 0d2f22e pushed by ngxson
1m 13s master
master
1m 13s
llama : support IBM Granite architecture (#9412) Python Type-Check #81: Commit 0d2ec43 pushed by ngxson
1m 43s master
master
1m 43s
convert : identify missing model files (#9397) Python Type-Check #80: Commit d54c21d pushed by ngxson
1m 33s master
master
1m 33s
common : reimplement logging (#9418) Python Type-Check #79: Commit 6262d13 pushed by ngxson
1m 10s master
master
1m 10s
py : add "LLaMAForCausalLM" conversion support (#9485) Python Type-Check #78: Commit 3c7989f pushed by ngxson
1m 13s master
master
1m 13s
server: add data: [DONE] to /chat/completions stream response (#9459) Python Type-Check #77: Commit dcdcee3 pushed by ngxson
1m 9s master
master
1m 9s
server : Add option to return token pieces in /tokenize endpoint (#9108) Python Type-Check #76: Commit 7820364 pushed by ngxson
20m 40s master
master
20m 40s
llava : fix the script error in MobileVLM README (#9054) Python Type-Check #75: Commit e665744 pushed by ngxson
1m 19s master
master
1m 19s
py : support converting local models (#7547) Python Type-Check #74: Commit 8db003a pushed by ngxson
1m 9s master
master
1m 9s
ProTip! You can narrow down the results and go further in time using created:<2024-09-11 or the other filters available.