Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
1,421 workflow runs
1,421 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : add NVPL BLAS support (#8329) (#8425) Server #164: Commit 3686456 pushed by ngxson
July 11, 2024 16:55 12m 36s master
master
July 11, 2024 16:55 12m 36s
CUDA: optimize and refactor MMQ (#8416) Server #163: Commit 808aba3 pushed by ngxson
July 11, 2024 14:55 8m 23s master
master
July 11, 2024 14:55 8m 23s
tokenize : add --no-parse-special option (#8423) Server #162: Commit 9a55ffe pushed by ngxson
July 11, 2024 07:55 8m 33s master
master
July 11, 2024 07:55 8m 33s
Initialize default slot sampling parameters from the global context. … Server #161: Commit 278d0e1 pushed by ngxson
July 11, 2024 00:55 8m 41s master
master
July 11, 2024 00:55 8m 41s
Name Migration: Build the deprecation-warning 'main' binary every tim… Server #160: Commit dd07a12 pushed by ngxson
July 10, 2024 17:52 8m 20s master
master
July 10, 2024 17:52 8m 20s
Xsn/fix lora Server #158: Pull request #7 opened by ngxson
July 8, 2024 14:55 8m 48s xsn/fix_lora
xsn/fix_lora
July 8, 2024 14:55 8m 48s
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#… Server #157: Commit f7cab35 pushed by ngxson
July 7, 2024 13:03 8m 15s master
master
July 7, 2024 13:03 8m 15s
llama : fix n_rot default (#8348) Server #156: Commit b504008 pushed by ngxson
July 7, 2024 12:03 8m 11s master
master
July 7, 2024 12:03 8m 11s
server: Retrieve prompt template in /props (#8337) Server #155: Commit cb4d86c pushed by ngxson
July 7, 2024 10:03 29m 49s master
master
July 7, 2024 10:03 29m 49s
added support for Authorization Bearer tokens when downloading model … Server #154: Commit 86e7299 pushed by ngxson
July 6, 2024 21:03 8m 13s master
master
July 6, 2024 21:03 8m 13s
llama : add early return for empty range (#8327) Server #153: Commit 87e25a1 pushed by ngxson
July 6, 2024 08:02 8m 54s master
master
July 6, 2024 08:02 8m 54s
Detokenizer fixes (#8039) Server #152: Commit 213701b pushed by ngxson
July 5, 2024 17:02 32m 19s master
master
July 5, 2024 17:02 32m 19s
llama : fix compile warning (#8304) Server #151: Commit 7ed03b8 pushed by ngxson
July 5, 2024 15:02 9m 31s master
master
July 5, 2024 15:02 9m 31s
Enabled more data types for oneMKL gemm_batch (#8236) Server #150: Commit 1f3e1b6 pushed by ngxson
July 5, 2024 13:02 10m 59s master
master
July 5, 2024 13:02 10m 59s
convert : remove AWQ remnants (#8320) Server #149: Commit 148ec97 pushed by ngxson
July 5, 2024 08:59 8m 14s master
master
July 5, 2024 08:59 8m 14s
cli: add EOT when user hit Ctrl+C (#8296) Server #148: Commit a38b884 pushed by ngxson
July 4, 2024 18:56 8m 42s master
master
July 4, 2024 18:56 8m 42s
convert : fix gemma v1 tokenizer convert (#8248) Server #147: Commit 20fc380 pushed by ngxson
July 4, 2024 08:57 8m 26s master
master
July 4, 2024 08:57 8m 26s
CUDA: refactor and optimize IQ MMVQ (#8215) Server #146: Commit cb5fad4 pushed by ngxson
July 1, 2024 19:25 10m 26s master
master
July 1, 2024 19:25 10m 26s
readme : update tool list (#8209) Server #145: Commit 0ddeff1 pushed by ngxson
July 1, 2024 15:53 19m 25s master
master
July 1, 2024 15:53 19m 25s
llama: Add attention and final logit soft-capping, update scaling fac… Server #144: Commit 1c5eba6 pushed by ngxson
June 30, 2024 16:09 8m 0s master
master
June 30, 2024 16:09 8m 0s
fix code typo in llama-cli (#8198) Server #143: Commit 72272b8 pushed by ngxson
June 29, 2024 08:38 7m 20s master
master
June 29, 2024 08:38 7m 20s
json: attempt to skip slow tests when running under emulator (#8189) Server #142: Commit 8748d8a pushed by ngxson
June 28, 2024 21:28 8m 21s master
master
June 28, 2024 21:28 8m 21s
llama: Add support for Gemma2ForCausalLM (#8156) Server #141: Commit e57dc62 pushed by ngxson
June 28, 2024 07:11 8m 0s master
master
June 28, 2024 07:11 8m 0s
Added support for Viking pre-tokenizer (#8135) Server #140: Commit f675b20 pushed by ngxson
June 27, 2024 10:30 29m 28s master
master
June 27, 2024 10:30 29m 28s
Update control vector help (#8104) Server #139: Commit f702a90 pushed by ngxson
June 25, 2024 08:54 8m 55s master
master
June 25, 2024 08:54 8m 55s
ProTip! You can narrow down the results and go further in time using created:<2024-06-25 or the other filters available.