Skip to content

Actions: ggerganov/llama.cpp

Code Coverage

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
12,192 workflow runs
12,192 workflow runs

Filter by Event

Loading

Filter by Status

Loading

Filter by Branch

Loading

Filter by Actor

Loading
chore: clean useless beam search param (#7985)
Code Coverage #13317: Commit b96f9af pushed by ggerganov
June 18, 2024 07:11 7m 37s master
June 18, 2024 07:11 7m 37s
readme : update UI list (#7943)
Code Coverage #13316: Commit 1193778 pushed by ggerganov
June 18, 2024 06:57 6m 22s master
June 18, 2024 06:57 6m 22s
ggml : sync
Code Coverage #13315: Commit 5326bcc pushed by ggerganov
June 18, 2024 06:50 3m 7s master
June 18, 2024 06:50 3m 7s
[SYCL] refactor
Code Coverage #13314: Pull request #6408 synchronize by airMeng
June 18, 2024 06:14 2m 26s sycl-refactor
June 18, 2024 06:14 2m 26s
fix workgroup size hardcode
Code Coverage #13313: Commit 167807d pushed by airMeng
June 18, 2024 06:14 1m 56s sycl-refactor
June 18, 2024 06:14 1m 56s
AVX IQ Quants
Code Coverage #13312: Pull request #7845 synchronize by netrunnereve
June 18, 2024 01:44 1m 58s netrunnereve:avx_iq
June 18, 2024 01:44 1m 58s
chore: clean useless beam search param
Code Coverage #13311: Pull request #7985 opened by thxCode
June 18, 2024 01:13 2m 1s thxCode:chore
June 18, 2024 01:13 2m 1s
update: support Qwen2-57B-A14B (#7835)
Code Coverage #13310: Commit a94e6ff pushed by slaren
June 17, 2024 19:08 2m 24s master
June 17, 2024 19:08 2m 24s
Refactor Vulkan backend to allow multiple contexts
Code Coverage #13309: Pull request #7961 synchronize by 0cc4m
June 17, 2024 18:58 2m 36s 0cc4m/vulkan-backend-context-fix
June 17, 2024 18:58 2m 36s
Tokenizer BPE fixes
Code Coverage #13307: Pull request #7530 synchronize by jaime-m-p
June 17, 2024 18:24 7m 46s jaime-m-p:tokenizer-bpe-fixes
June 17, 2024 18:24 7m 46s
Make updates to type cast based on compiler instead of OS (#7851)
Code Coverage #13306: Commit 5b6da18 pushed by slaren
June 17, 2024 18:23 4m 26s master
June 17, 2024 18:23 4m 26s
llama : disable FA if KV head size do not match (#7982)
Code Coverage #13305: Commit 7c26775 pushed by ggerganov
June 17, 2024 16:40 2m 25s master
June 17, 2024 16:40 2m 25s
llama : disable FA if KV head size do not match
Code Coverage #13304: Pull request #7982 opened by ggerganov
June 17, 2024 16:21 10m 37s gg/fa-req-kq-hs
June 17, 2024 16:21 10m 37s
llama : disable FA if KV head size do not match
Code Coverage #13303: Commit ef79941 pushed by ggerganov
June 17, 2024 16:20 9m 12s gg/fa-req-kq-hs
June 17, 2024 16:20 9m 12s
sycl-exp : Temporarily revert RPC offload (#7640)
Code Coverage #13302: Pull request #7981 opened by joeatodd
June 17, 2024 16:12 9m 44s codeplay/temp-rpc-revert
June 17, 2024 16:12 9m 44s
Add Nix and Flox install instructions (#7899)
Code Coverage #13298: Commit b473e95 pushed by HanClinto
June 17, 2024 15:37 2m 57s master
June 17, 2024 15:37 2m 57s
[no ci] Add Nix and Flox install instructions
Code Coverage #13297: Pull request #7899 synchronize by bryanhonof
June 17, 2024 15:28 2m 18s bryanhonof:master
June 17, 2024 15:28 2m 18s
sched : offload_op also requires supports_op (#7977)
Code Coverage #13296: Commit 99052cd pushed by slaren
June 17, 2024 14:51 3m 5s master
June 17, 2024 14:51 3m 5s
fix: divide 0 exception in mamba (#7932)
Code Coverage #13295: Commit c637fcd pushed by slaren
June 17, 2024 14:11 6m 1s master
June 17, 2024 14:11 6m 1s
Implement non-mapped async IO for CUDA on Windows. (#7896)
Code Coverage #13294: Commit 6a2f0b3 pushed by slaren
June 17, 2024 14:10 2m 15s master
June 17, 2024 14:10 2m 15s
sched : offload_op also requires supports_op
Code Coverage #13293: Pull request #7977 opened by slaren
June 17, 2024 14:05 2m 24s sl/sched-supports-offload
June 17, 2024 14:05 2m 24s