Skip to content

Actions: ngxson/llama.cpp

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
230 workflow runs
230 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : Add support for DeepSeek V3 (#11049)
Python Type-Check #232: Commit 9394bbd pushed by ngxson
January 4, 2025 20:10 1m 13s master
January 4, 2025 20:10 1m 13s
llama : add support for the cohere2 model architecture (#10900)
Python Type-Check #231: Commit 46be942 pushed by ngxson
January 4, 2025 14:37 1m 10s master
January 4, 2025 14:37 1m 10s
server: bench: minor fixes (#10765)
Python Type-Check #230: Commit 2f0ee84 pushed by ngxson
January 2, 2025 17:10 1m 12s master
January 2, 2025 17:10 1m 12s
server : allow using LoRA adapters per-request (#10994)
Python Type-Check #229: Commit 0da5d86 pushed by ngxson
January 2, 2025 14:08 3m 40s master
January 2, 2025 14:08 3m 40s
move lora change task to queue
Python Type-Check #228: Commit 1dbd16a pushed by ngxson
January 1, 2025 18:59 1m 15s xsn/lora_per_request
January 1, 2025 18:59 1m 15s
add slow test with llama 8b
Python Type-Check #227: Commit 367f0ab pushed by ngxson
January 1, 2025 18:36 1m 14s xsn/lora_per_request
January 1, 2025 18:36 1m 14s
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)
Python Type-Check #226: Commit 0827b2c pushed by ngxson
December 31, 2024 14:25 1m 22s master
December 31, 2024 14:25 1m 22s
server : add OAI compat for /v1/completions (#10974)
Python Type-Check #225: Commit 5896c65 pushed by ngxson
December 31, 2024 11:34 1m 18s master
December 31, 2024 11:34 1m 18s
add chat template test
Python Type-Check #224: Commit c6bd7a7 pushed by ngxson
December 31, 2024 11:30 1m 14s xsn/server_chat_template_detect
December 31, 2024 11:30 1m 14s
convert : fix Llama-3_1-Nemotron-51B rope settings (#11008)
Python Type-Check #223: Commit bc7b1f8 pushed by ngxson
December 31, 2024 11:09 1m 12s master
December 31, 2024 11:09 1m 12s
fix condition
Python Type-Check #222: Commit 076346d pushed by ngxson
December 28, 2024 15:17 4m 15s xsn/lora_per_request
December 28, 2024 15:17 4m 15s
move can_batch_with check
Python Type-Check #221: Commit b9b2b63 pushed by ngxson
December 27, 2024 19:22 1m 13s xsn/lora_per_request
December 27, 2024 19:22 1m 13s
test: force disable cache prompt
Python Type-Check #220: Commit 9947b07 pushed by ngxson
December 27, 2024 17:35 1m 28s xsn/lora_per_request
December 27, 2024 17:35 1m 28s
lora per request
Python Type-Check #219: Commit 9d84127 pushed by ngxson
December 27, 2024 15:11 1m 11s xsn/lora_per_request
December 27, 2024 15:11 1m 11s
add test
Python Type-Check #218: Commit 3603399 pushed by ngxson
December 25, 2024 13:41 1m 24s xsn/oai_completions
December 25, 2024 13:41 1m 24s
server : add support for "encoding_format": "base64" to the */embeddi…
Python Type-Check #217: Commit 9ba399d pushed by ngxson
December 24, 2024 20:37 1m 25s master
December 24, 2024 20:37 1m 25s
ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
Python Type-Check #216: Commit 2cd43f4 pushed by ngxson
December 24, 2024 17:56 1m 24s master
December 24, 2024 17:56 1m 24s
server: allow filtering llama server response fields (#10940)
Python Type-Check #215: Commit 09fe2e7 pushed by ngxson
December 24, 2024 16:40 1m 12s master
December 24, 2024 16:40 1m 12s
server : add system_fingerprint to chat/completion (#10917)
Python Type-Check #214: Commit 485dc01 pushed by ngxson
December 23, 2024 11:03 1m 13s master
December 23, 2024 11:03 1m 13s
llama : support InfiniAI Megrez 3b (#10893)
Python Type-Check #213: Commit b92a14a pushed by ngxson
December 23, 2024 01:35 1m 10s master
December 23, 2024 01:35 1m 10s
llama : support for Llama-3_1-Nemotron-51B (#10669)
Python Type-Check #212: Commit 6f0c9e0 pushed by ngxson
December 23, 2024 00:35 1m 17s master
December 23, 2024 00:35 1m 17s
devops : add docker-multi-stage builds (#10832)
Python Type-Check #211: Commit 7c0e285 pushed by ngxson
December 22, 2024 22:35 1m 27s master
December 22, 2024 22:35 1m 27s
convert : add BertForMaskedLM (#10919)
Python Type-Check #210: Commit 5cd85b5 pushed by ngxson
December 21, 2024 08:32 1m 16s master
December 21, 2024 08:32 1m 16s
server : add system_fingerprint to chat/completion
Python Type-Check #209: Commit 44e9a47 pushed by ngxson
December 20, 2024 11:42 1m 21s xsn/oai_add_system_fingerprint
December 20, 2024 11:42 1m 21s
convert : fix RWKV v6 model conversion (#10913)
Python Type-Check #208: Commit 0a11f8b pushed by ngxson
December 20, 2024 10:25 1m 12s master
December 20, 2024 10:25 1m 12s