Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
11,750 workflow runs
11,750 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

quantize: improve pattern matching for allowed tensors Server #13456: Pull request #13033 synchronize by EAddario
May 3, 2025 06:17 8m 22s EAddario:quantize
EAddario:quantize
May 3, 2025 06:17 8m 22s
sampling: Integrate Top-nσ into main sampling chain (and add it to the server) Server #13455: Pull request #13264 synchronize by oobabooga
May 3, 2025 02:52 7m 19s oobabooga:nsigma
oobabooga:nsigma
May 3, 2025 02:52 7m 19s
feat: First pass at llama_kv_cache_hybrid Server #13454: Pull request #13276 opened by gabe-l-hart
May 2, 2025 23:08 4m 46s gabe-l-hart:HybridCache
gabe-l-hart:HybridCache
May 2, 2025 23:08 4m 46s
llama : initial Mamba-2 support Server #13453: Pull request #9126 synchronize by compilade
May 2, 2025 22:29 3m 36s compilade/mamba2
compilade/mamba2
May 2, 2025 22:29 3m 36s
mtmd : add C public API Server #13452: Pull request #13184 synchronize by ngxson
May 2, 2025 20:39 8m 40s ngxson:xsn/mtmd_c_api
ngxson:xsn/mtmd_c_api
May 2, 2025 20:39 8m 40s
mtmd : add C public API Server #13451: Pull request #13184 synchronize by ngxson
May 2, 2025 20:25 9m 58s ngxson:xsn/mtmd_c_api
ngxson:xsn/mtmd_c_api
May 2, 2025 20:25 9m 58s
clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking change) Server #13450: Pull request #13259 synchronize by ngxson
May 2, 2025 19:50 8m 32s ngxson:xsn/revert_rm_boi_eoi
ngxson:xsn/revert_rm_boi_eoi
May 2, 2025 19:50 8m 32s
llama : move end-user examples to tools directory (#13249) Server #13449: Commit 1d36b36 pushed by slaren
May 2, 2025 18:27 14m 22s master
master
May 2, 2025 18:27 14m 22s
sync : ggml (#13268) Server #13448: Commit b344439 pushed by ggerganov
May 2, 2025 17:54 17m 57s master
master
May 2, 2025 17:54 17m 57s
context : fix reorder logic (#13267) Server #13447: Commit a75cb30 pushed by ggerganov
May 2, 2025 17:54 10m 54s master
master
May 2, 2025 17:54 10m 54s
sync : ggml Server #13446: Pull request #13268 synchronize by ggerganov
May 2, 2025 16:55 21m 44s sync-ggml-25-05-02
sync-ggml-25-05-02
May 2, 2025 16:55 21m 44s
ggml : Enable MMA for BF16 in llamafile_sgemm (#13148) Server #13445: Commit 3f3769b pushed by ggerganov
May 2, 2025 16:53 26m 50s master
master
May 2, 2025 16:53 26m 50s
Model: Granite MoE shared Server #13444: Pull request #13269 opened by gabe-l-hart
May 2, 2025 16:20 41m 41s gabe-l-hart:GraniteMoEShared
gabe-l-hart:GraniteMoEShared
May 2, 2025 16:20 41m 41s
sync : ggml Server #13443: Pull request #13268 opened by ggerganov
May 2, 2025 16:03 45m 44s sync-ggml-25-05-02
sync-ggml-25-05-02
May 2, 2025 16:03 45m 44s
context : fix reorder logic Server #13442: Pull request #13267 opened by ggerganov
May 2, 2025 15:59 22m 59s gg/context-fix-reorder
gg/context-fix-reorder
May 2, 2025 15:59 22m 59s
llama : initial Mamba-2 support Server #13441: Pull request #9126 synchronize by compilade
May 2, 2025 15:56 18m 53s compilade/mamba2
compilade/mamba2
May 2, 2025 15:56 18m 53s
sampling: Integrate Top-nσ into main sampling chain (and add it to the server) Server #13440: Pull request #13264 synchronize by oobabooga
May 2, 2025 15:46 14m 34s oobabooga:nsigma
oobabooga:nsigma
May 2, 2025 15:46 14m 34s
llama-model : support Qwen2 embedding models and pooling_mode_lasttok… Server #13439: Commit 2f56761 pushed by cebtenzzre
May 2, 2025 15:42 15m 13s master
master
May 2, 2025 15:42 15m 13s
vulkan: Additional type support for unary, binary, and copy Server #13438: Pull request #13266 opened by jeffbolznv
May 2, 2025 15:07 25m 21s jeffbolznv:f16_add_cpy_unary
jeffbolznv:f16_add_cpy_unary
May 2, 2025 15:07 25m 21s
sampling: Integrate Top-nσ into main sampling chain (and add it to the server) Server #13437: Pull request #13264 opened by oobabooga
May 2, 2025 14:31 35m 53s oobabooga:nsigma
oobabooga:nsigma
May 2, 2025 14:31 35m 53s
sycl: use oneDNN for matrices multiplication Server #13436: Pull request #12972 synchronize by lslusarczyk
May 2, 2025 14:16 17m 36s lslusarczyk:todnn
lslusarczyk:todnn
May 2, 2025 14:16 17m 36s
llama : move end-user examples to tools directory Server #13435: Pull request #13249 synchronize by ngxson
May 2, 2025 13:55 16m 43s sl/move-tools
sl/move-tools
May 2, 2025 13:55 16m 43s
llama : move end-user examples to tools directory Server #13434: Pull request #13249 synchronize by slaren
May 2, 2025 13:51 4m 56s sl/move-tools
sl/move-tools
May 2, 2025 13:51 4m 56s
cmake: simplify vulkan shader test logic Server #13433: Pull request #13263 synchronize by bandoti
May 2, 2025 13:38 18m 58s bandoti:cmake-vulkan-test-shader-func
bandoti:cmake-vulkan-test-shader-func
May 2, 2025 13:38 18m 58s
llama : move end-user examples to tools directory Server #13432: Pull request #13249 synchronize by slaren
May 2, 2025 13:29 8m 5s sl/move-tools
sl/move-tools
May 2, 2025 13:29 8m 5s
ProTip! You can narrow down the results and go further in time using created:<2025-05-02 or the other filters available.