Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
1,171 workflow run results
1,171 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

main: add test-cli + ensure completion goes to stdout even w/ --log-disable CI #16278: Pull request #10102 opened by ochafik
49m 42s ochafik:test-cli
ochafik:test-cli
49m 42s
llama : enable flash attn automatically when supported (WIP) CI #16277: Pull request #10101 opened by slaren
50m 33s sl/auto-flash-attn
sl/auto-flash-attn
50m 33s
ggml : check tensor name lengths in gguf files CI #16276: Pull request #10100 opened by slaren
48m 28s sl/fix-gguf-tensor-name-len
sl/fix-gguf-tensor-name-len
48m 28s
add FP8 support to gguf/llama: CI #16275: Pull request #10055 synchronize by Djip007
1h 5m 56s Djip007:feature/fp8
Djip007:feature/fp8
1h 5m 56s
llama : improve output buffer type selection CI #16274: Pull request #10098 opened by slaren
54m 6s sl/fix-output-buffer-alloc
sl/fix-output-buffer-alloc
54m 6s
add FP8 support to gguf/llama: CI #16273: Pull request #10055 synchronize by Djip007
55m 48s Djip007:feature/fp8
Djip007:feature/fp8
55m 48s
add FP8 support to gguf/llama: CI #16272: Pull request #10055 synchronize by Djip007
1m 33s Djip007:feature/fp8
Djip007:feature/fp8
1m 33s
add FP8 support to gguf/llama: CI #16271: Pull request #10055 synchronize by Djip007
1m 0s Djip007:feature/fp8
Djip007:feature/fp8
1m 0s
add FP8 support to gguf/llama: CI #16270: Pull request #10055 synchronize by Djip007
37s Djip007:feature/fp8
Djip007:feature/fp8
37s
add FP8 support to gguf/llama: CI #16269: Pull request #10055 synchronize by Djip007
18s Djip007:feature/fp8
Djip007:feature/fp8
18s
add FP8 support to gguf/llama: CI #16268: Pull request #10055 synchronize by Djip007
1m 58s Djip007:feature/fp8
Djip007:feature/fp8
1m 58s
kompute: add mul_mat_q4_k shader CI #16267: Pull request #10097 opened by slp
1h 7m 26s slp:kompute-q4-k-v3
slp:kompute-q4-k-v3
1h 7m 26s
kompute: add backend registry / device interfaces (#10045) CI #16266: Commit 61408e7 pushed by slaren
1h 2m 12s master
master
1h 2m 12s
kompute: add backend registry / device interfaces and Q4_K shader CI #16265: Pull request #10045 synchronize by slp
56m 28s slp:kompute-regdev
slp:kompute-regdev
56m 28s
sampling: add K-Shift sampler CI #16264: Pull request #10048 synchronize by MaggotHATE
46m 58s MaggotHATE:k-shift2
MaggotHATE:k-shift2
46m 58s
ggml : fix memory leaks when loading invalid gguf files (#10094) CI #16263: Commit b9e02e8 pushed by slaren
1h 2m 16s master
master
1h 2m 16s
ggml : fix memory leaks when loading invalid gguf files CI #16262: Pull request #10094 synchronize by slaren
55m 40s sl/fix-gguf-leak
sl/fix-gguf-leak
55m 40s
ggml : fix memory leaks when loading invalid gguf files CI #16261: Pull request #10094 synchronize by slaren
13m 31s sl/fix-gguf-leak
sl/fix-gguf-leak
13m 31s
ggml : fix memory leaks when loading invalid gguf files CI #16260: Pull request #10094 synchronize by slaren
8m 25s sl/fix-gguf-leak
sl/fix-gguf-leak
8m 25s
ggml : fix memory leaks when loading invalid gguf files CI #16259: Pull request #10094 opened by slaren
2m 46s sl/fix-gguf-leak
sl/fix-gguf-leak
2m 46s
ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (#10029) CI #16258: Commit fc83a9e pushed by ggerganov
1h 46m 21s master
master
1h 46m 21s
ggml : Implementations for Q4_0_8_8 quantization based functions - RISC-V vector version CI #16257: Pull request #10029 synchronize by xctan
2h 3m 0s xctan:rvv_q4_0_8x8
xctan:rvv_q4_0_8x8
2h 3m 0s
sampling: add K-Shift sampler CI #16256: Pull request #10048 synchronize by MaggotHATE
59m 35s MaggotHATE:k-shift2
MaggotHATE:k-shift2
59m 35s
llama : refactor model loader with backend registry (#10026) CI #16255: Commit c5b0f4b pushed by slaren
1h 7m 32s master
master
1h 7m 32s
sampling: add K-Shift sampler CI #16254: Pull request #10048 synchronize by MaggotHATE
53m 17s MaggotHATE:k-shift2
MaggotHATE:k-shift2
53m 17s