Skip to content

Actions: ggerganov/llama.cpp

Nix CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
9,937 workflow runs
9,937 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : check that the prompt fits in the slot's context (#10030)
Nix CI #11039: Commit bc5ba00 pushed by ggerganov
October 25, 2024 07:13 Queued master
October 25, 2024 07:13 Queued
server : check that the prompt fits in the slot's context
Nix CI #11038: Pull request #10030 synchronize by ggerganov
October 25, 2024 07:13 In progress gg/server-check-ctx
October 25, 2024 07:13 In progress
llama : refactor model loader with backend registry
Nix CI #11036: Pull request #10026 synchronize by slaren
October 25, 2024 00:59 21m 22s sl/load-time-supports-op
October 25, 2024 00:59 21m 22s
llama : refactor model loader with backend registry
Nix CI #11034: Pull request #10026 synchronize by slaren
October 24, 2024 22:06 17m 49s sl/load-time-supports-op
October 24, 2024 22:06 17m 49s
llama : refactor model loader with backend registry
Nix CI #11033: Pull request #10026 synchronize by slaren
October 24, 2024 22:04 4m 19s sl/load-time-supports-op
October 24, 2024 22:04 4m 19s
llama : refactor model loader with backend registry
Nix CI #11032: Pull request #10026 synchronize by slaren
October 24, 2024 21:47 5m 12s sl/load-time-supports-op
October 24, 2024 21:47 5m 12s
server : refactor slot input data, move tokenizer to HTTP thread (#10…
Nix CI #11031: Commit 958367b pushed by ngxson
October 24, 2024 19:51 11m 29s master
October 24, 2024 19:51 11m 29s
ci : fix cmake flags for SYCL
Nix CI #11030: Commit 40f2555 pushed by ggerganov
October 24, 2024 18:23 6m 46s master
October 24, 2024 18:23 6m 46s
Make Kompute error verbose about unsupported types
Nix CI #11027: Pull request #10034 opened by ericcurtin
October 24, 2024 14:40 22m 42s ericcurtin:kompute-debug
October 24, 2024 14:40 22m 42s
CUDA: fix insufficient buffer clearing for MMQ (#10032)
Nix CI #11024: Commit 167a515 pushed by JohannesGaessler
October 24, 2024 12:40 6m 32s master
October 24, 2024 12:40 6m 32s
metal : support permuted matrix multiplicaions
Nix CI #11023: Pull request #10033 opened by ggerganov
October 24, 2024 12:27 6m 24s gg/metal-mm-permute-support
October 24, 2024 12:27 6m 24s
CUDA: fix MMQ for non-contiguous src0, add tests (#10021)
Nix CI #11020: Commit c39665f pushed by JohannesGaessler
October 24, 2024 09:09 6m 21s master
October 24, 2024 09:09 6m 21s
server : check that the prompt fits in the slot's context
Nix CI #11019: Pull request #10030 opened by ggerganov
October 24, 2024 08:06 6m 20s gg/server-check-ctx
October 24, 2024 08:06 6m 20s
ggml : Implementations for Q4_0_8_8 quantization based functions - RISC-V vector version
Nix CI #11017: Pull request #10029 opened by xctan
October 24, 2024 07:12 Action required xctan:rvv_q4_0_8x8
October 24, 2024 07:12 Action required