Skip to content

Actions: ngxson/llama.cpp

Actions

flake8 Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-lint.yml
1,189 workflow runs
1,189 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : add support for "encoding_format": "base64" to the */embeddi… flake8 Lint #1175: Commit 9ba399d pushed by ngxson
December 24, 2024 20:37 20s master
master
December 24, 2024 20:37 20s
ggml : more perfo with llamafile tinyblas on x86_64 (#10714) flake8 Lint #1174: Commit 2cd43f4 pushed by ngxson
December 24, 2024 17:56 21s master
master
December 24, 2024 17:56 21s
server: allow filtering llama server response fields (#10940) flake8 Lint #1173: Commit 09fe2e7 pushed by ngxson
December 24, 2024 16:40 25s master
master
December 24, 2024 16:40 25s
server : add system_fingerprint to chat/completion (#10917) flake8 Lint #1172: Commit 485dc01 pushed by ngxson
December 23, 2024 11:03 23s master
master
December 23, 2024 11:03 23s
llama : support InfiniAI Megrez 3b (#10893) flake8 Lint #1171: Commit b92a14a pushed by ngxson
December 23, 2024 01:35 21s master
master
December 23, 2024 01:35 21s
llama : support for Llama-3_1-Nemotron-51B (#10669) flake8 Lint #1170: Commit 6f0c9e0 pushed by ngxson
December 23, 2024 00:35 21s master
master
December 23, 2024 00:35 21s
devops : add docker-multi-stage builds (#10832) flake8 Lint #1169: Commit 7c0e285 pushed by ngxson
December 22, 2024 22:35 4m 57s master
master
December 22, 2024 22:35 4m 57s
convert : add BertForMaskedLM (#10919) flake8 Lint #1168: Commit 5cd85b5 pushed by ngxson
December 21, 2024 08:32 24s master
master
December 21, 2024 08:32 24s
convert : fix RWKV v6 model conversion (#10913) flake8 Lint #1167: Commit 0a11f8b pushed by ngxson
December 20, 2024 10:25 22s master
master
December 20, 2024 10:25 22s
ggml: fix arm build with gcc (#10895) flake8 Lint #1166: Commit a3c33b1 pushed by ngxson
December 19, 2024 13:25 24s master
master
December 19, 2024 13:25 24s
convert : Add support for Microsoft Phi-4 model (#10817) flake8 Lint #1165: Commit 7585edb pushed by ngxson
December 19, 2024 10:25 3m 31s master
master
December 19, 2024 10:25 3m 31s
server : add "tokens" output (#10853) flake8 Lint #1164: Commit 0e70ba6 pushed by ngxson
December 18, 2024 09:24 25s master
master
December 18, 2024 09:24 25s
Revert "llama : add Falcon3 support (#10864)" (#10876) flake8 Lint #1163: Commit 4da69d1 pushed by ngxson
December 18, 2024 01:24 22s master
master
December 18, 2024 01:24 22s
server : fill usage info in embeddings and rerank responses (#10852) flake8 Lint #1162: Commit 05c3a44 pushed by ngxson
December 17, 2024 16:23 27s master
master
December 17, 2024 16:23 27s
llava : Allow locally downloaded models for QwenVL (#10833) flake8 Lint #1161: Commit 4ddd199 pushed by ngxson
December 15, 2024 21:22 20s master
master
December 15, 2024 21:22 20s
llama : add Deepseek MoE v1 & GigaChat models (#10827) flake8 Lint #1160: Commit a097415 pushed by ngxson
December 15, 2024 17:22 26s master
master
December 15, 2024 17:22 26s
server: Fix has_next_line in JSON response (#10818) flake8 Lint #1159: Commit 89d604f pushed by ngxson
December 14, 2024 23:21 22s master
master
December 14, 2024 23:21 22s
llama : add Qwen2VL support + multimodal RoPE (#10361) flake8 Lint #1158: Commit ba1cb19 pushed by ngxson
December 14, 2024 13:21 27s master
master
December 14, 2024 13:21 27s
Introducing experimental OpenCL backend with support for Qualcomm Adr… flake8 Lint #1157: Commit a76c56f pushed by ngxson
December 13, 2024 21:20 24s master
master
December 13, 2024 21:20 24s
gguf-py : numpy 2 newbyteorder fix (#9772) flake8 Lint #1156: Commit 4601a8b pushed by ngxson
December 13, 2024 15:20 27s master
master
December 13, 2024 15:20 27s
imatrix : Add imatrix to --no-context-shift (#10766) flake8 Lint #1155: Commit ae4b922 pushed by ngxson
December 10, 2024 18:18 7m 38s master
master
December 10, 2024 18:18 7m 38s
server : fix format_infill (#10724) flake8 Lint #1154: Commit ce8784b pushed by ngxson
December 8, 2024 22:16 19s master
master
December 8, 2024 22:16 19s
server : bring back info of final chunk in stream mode (#10722) flake8 Lint #1153: Commit e52522b pushed by ngxson
December 8, 2024 20:16 23s master
master
December 8, 2024 20:16 23s
llama : add 128k yarn context for Qwen (#10698) flake8 Lint #1152: Commit 62e84d9 pushed by ngxson
December 7, 2024 21:16 1m 9s master
master
December 7, 2024 21:16 1m 9s
server : (refactor) no more json in server_task input (#10691) flake8 Lint #1151: Commit 3573fa8 pushed by ngxson
December 7, 2024 20:15 21s master
master
December 7, 2024 20:15 21s