Skip to content

Actions: ggerganov/llama.cpp

Publish Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
8,372 workflow run results
8,372 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

common : preallocate sampling token data vector (#8363)
Publish Docker image #14203: Commit 470939d pushed by ggerganov
July 8, 2024 07:26 2h 40m 8s master
July 8, 2024 07:26 2h 40m 8s
infill : assert prefix/suffix tokens + remove old space logic (#8351)
Publish Docker image #14202: Commit 6f0dbf6 pushed by ggerganov
July 8, 2024 06:34 2h 29m 42s master
July 8, 2024 06:34 2h 29m 42s
common : avoid unnecessary logits fetch (#8358)
Publish Docker image #14201: Commit ffd0079 pushed by ggerganov
July 8, 2024 06:31 1h 55m 56s master
July 8, 2024 06:31 1h 55m 56s
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#…
Publish Docker image #14200: Commit f7cab35 pushed by mofosyne
July 7, 2024 12:58 2h 58m 28s master
July 7, 2024 12:58 2h 58m 28s
llama : support glm3 and glm4 (#8031)
Publish Docker image #14199: Commit 905942a pushed by ggerganov
July 7, 2024 12:52 2h 2m 2s master
July 7, 2024 12:52 2h 2m 2s
llama : fix n_rot default (#8348)
Publish Docker image #14198: Commit b504008 pushed by ggerganov
July 7, 2024 11:59 2h 26m 38s master
July 7, 2024 11:59 2h 26m 38s
server: Retrieve prompt template in /props (#8337)
Publish Docker image #14197: Commit cb4d86c pushed by ngxson
July 7, 2024 09:10 1h 59m 44s master
July 7, 2024 09:10 1h 59m 44s
added support for Authorization Bearer tokens when downloading model …
Publish Docker image #14196: Commit 86e7299 pushed by ngxson
July 6, 2024 20:32 1h 54m 33s master
July 6, 2024 20:32 1h 54m 33s
llama : add early return for empty range (#8327)
Publish Docker image #14195: Commit 87e25a1 pushed by ggerganov
July 6, 2024 07:22 2h 16m 37s master
July 6, 2024 07:22 2h 16m 37s
Detokenizer fixes (#8039)
Publish Docker image #14194: Commit 213701b pushed by jaime-m-p
July 5, 2024 17:01 1h 56m 52s master
July 5, 2024 17:01 1h 56m 52s
llama : fix compile warning (#8304)
Publish Docker image #14193: Commit 7ed03b8 pushed by ggerganov
July 5, 2024 14:32 2h 25m 17s master
July 5, 2024 14:32 2h 25m 17s
cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
Publish Docker image #14192: Commit 1d894a7 pushed by ggerganov
July 5, 2024 14:29 1h 58m 19s master
July 5, 2024 14:29 1h 58m 19s
Enabled more data types for oneMKL gemm_batch (#8236)
Publish Docker image #14191: Commit 1f3e1b6 pushed by AidanBeltonS
July 5, 2024 12:23 2h 10m 5s master
July 5, 2024 12:23 2h 10m 5s
CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
Publish Docker image #14190: Commit 8e55830 pushed by JohannesGaessler
July 5, 2024 07:06 3h 59m 9s master
July 5, 2024 07:06 3h 59m 9s
CUDA: revert part of the RDNA1 optimizations (#8309)
Publish Docker image #14189: Commit 0a42380 pushed by JohannesGaessler
July 5, 2024 07:06 3h 6m 2s master
July 5, 2024 07:06 3h 6m 2s
llama : streamline embeddings from "non-embedding" models (#8087)
Publish Docker image #14188: Commit d12f781 pushed by ggerganov
July 5, 2024 07:05 2h 30m 25s master
July 5, 2024 07:05 2h 30m 25s
CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311)
Publish Docker image #14187: Commit bcefa03 pushed by JohannesGaessler
July 5, 2024 07:05 1h 54m 32s master
July 5, 2024 07:05 1h 54m 32s
llama : prefer n_ over num_ prefix (#8308)
Publish Docker image #14186: Commit aa5898d pushed by ggerganov
July 5, 2024 06:10 1h 45m 0s master
July 5, 2024 06:10 1h 45m 0s
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
Publish Docker image #14185: Commit a9554e2 pushed by airMeng
July 5, 2024 05:06 1h 49m 39s master
July 5, 2024 05:06 1h 49m 39s
rm get_work_group_size() by local cache for performance (#8286)
Publish Docker image #14184: Commit f09b7cb pushed by NeoZhangJianyu
July 5, 2024 02:32 1h 56m 44s master
July 5, 2024 02:32 1h 56m 44s
cli: add EOT when user hit Ctrl+C (#8296)
Publish Docker image #14183: Commit a38b884 pushed by ngxson
July 4, 2024 18:55 2h 50m 46s master
July 4, 2024 18:55 2h 50m 46s
llama : add OpenELM support (#7359)
Publish Docker image #14182: Commit d7fd29f pushed by ggerganov
July 4, 2024 17:14 2h 58m 49s master
July 4, 2024 17:14 2h 58m 49s
tokenize : add --show-count (token) option (#8299)
Publish Docker image #14181: Commit 6f63d64 pushed by ggerganov
July 4, 2024 16:39 2h 53m 54s master
July 4, 2024 16:39 2h 53m 54s
build: Export hf-to-gguf as snakecase
Publish Docker image #14180: Commit 51d2eba pushed by SomeoneSerge
July 4, 2024 15:39 2h 24m 14s master
July 4, 2024 15:39 2h 24m 14s
Inference support for T5 and FLAN-T5 model families (#5763)
Publish Docker image #14179: Commit 807b0c4 pushed by fairydreaming
July 4, 2024 13:46 2h 7m 56s master
July 4, 2024 13:46 2h 7m 56s
ProTip! You can narrow down the results and go further in time using created:<2024-07-04 or the other filters available.