Skip to content

Actions: ggerganov/llama.cpp

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
1,002 workflow runs
1,002 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor/online repacking
Python Type-Check #1081: Pull request #10446 synchronize by Djip007
December 4, 2024 22:54 12m 31s Djip007:refactor/online_repacking
December 4, 2024 22:54 12m 31s
Refactor/online repacking
Python Type-Check #1079: Pull request #10446 synchronize by Djip007
December 4, 2024 22:39 1m 12s Djip007:refactor/online_repacking
December 4, 2024 22:39 1m 12s
server : fix speculative decoding with context shift (#10641)
Python Type-Check #1078: Commit 1da7b76 pushed by ggerganov
December 4, 2024 20:38 1m 9s master
December 4, 2024 20:38 1m 9s
server : fix speculative decoding with context shift
Python Type-Check #1072: Pull request #10641 synchronize by ggerganov
December 4, 2024 11:11 1m 22s gg/server-fix-spec-ctx-shift
December 4, 2024 11:11 1m 22s
server : add tests
Python Type-Check #1071: Commit 81611be pushed by ggerganov
December 4, 2024 11:11 1m 29s gg/server-fix-spec-ctx-shift
December 4, 2024 11:11 1m 29s
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
Python Type-Check #1070: Commit 8d0cfd5 pushed by ggerganov
December 4, 2024 09:42 14m 23s master
December 4, 2024 09:42 14m 23s
gguf-py: Improve GGUFReader read-only mode performance
Python Type-Check #1069: Pull request #10159 synchronize by Isotr0py
December 4, 2024 07:25 1m 10s Isotr0py:gguf-reader-improve
December 4, 2024 07:25 1m 10s
Add support for GLM-Edge and GLM-Edge-V series models
Python Type-Check #1068: Pull request #10573 synchronize by piDack
December 4, 2024 03:50 1m 10s piDack:support_glm_edge_model
December 4, 2024 03:50 1m 10s
Add support for GLM-Edge and GLM-Edge-V series models
Python Type-Check #1067: Pull request #10573 synchronize by piDack
December 4, 2024 03:33 1m 11s piDack:support_glm_edge_model
December 4, 2024 03:33 1m 11s
ggml-cpu : fix HWCAP2_I8MM value
Python Type-Check #1066: Commit 88cf9f9 pushed by slaren
December 4, 2024 00:39 1m 7s sl/fix-HWCAP2_I8MM
December 4, 2024 00:39 1m 7s
server: add OpenAI compatible response format for legacy /completions with b…
Python Type-Check #1065: Pull request #10645 opened by Nero7991
December 4, 2024 00:17 Action required Nero7991:oai_legacy_completion
December 4, 2024 00:17 Action required
Vulkan: Add VK_AMD_shader_core_properties2 support to read Compute Un…
Python Type-Check #1064: Commit 7002d6c pushed by 0cc4m
December 3, 2024 20:23 1m 32s 0cc4m/vulkan-coopmat
December 3, 2024 20:23 1m 32s
Add support for GLM-Edge and GLM-Edge-V series models
Python Type-Check #1063: Pull request #10573 synchronize by piDack
December 3, 2024 11:23 10m 9s piDack:support_glm_edge_model
December 3, 2024 11:23 10m 9s
Add support for GLM-Edge and GLM-Edge-V series models
Python Type-Check #1062: Pull request #10573 synchronize by piDack
December 3, 2024 05:27 1m 7s piDack:support_glm_edge_model
December 3, 2024 05:27 1m 7s
opencl: Clean up small-alloc in CMake files
Python Type-Check #1061: Commit 3e74c27 pushed by max-krasnyansky
December 3, 2024 00:34 7m 6s adreno-support
December 3, 2024 00:34 7m 6s
fixes
Python Type-Check #1060: Commit e48c2eb pushed by slaren
December 3, 2024 00:31 1m 9s sl/dl-backend-6
December 3, 2024 00:31 1m 9s
server: Add "tokens per second" information in the backend (#10548)
Python Type-Check #1059: Commit 64ed209 pushed by ngxson
December 2, 2024 13:45 1m 25s master
December 2, 2024 13:45 1m 25s
remove redundant code
Python Type-Check #1058: Commit a1b99b9 pushed by ngxson
December 2, 2024 12:35 5m 44s token
December 2, 2024 12:35 5m 44s
server: Add "tokens per second" information in the backend
Python Type-Check #1057: Pull request #10548 synchronize by ngxson
December 2, 2024 12:34 1m 12s lhpqaq:token
December 2, 2024 12:34 1m 12s