Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
950 workflow run results
950 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : refactor model loader with backend registry CI #16253: Pull request #10026 synchronize by slaren
1h 1m 14s sl/load-time-supports-op
sl/load-time-supports-op
1h 1m 14s
kompute: add backend registry / device interfaces and Q4_K shader CI #16252: Pull request #10045 synchronize by slp
1h 6m 43s slp:kompute-regdev
slp:kompute-regdev
1h 6m 43s
kompute: add backend registry / device interfaces and Q4_K shader CI #16251: Pull request #10045 synchronize by slp
48m 11s slp:kompute-regdev
slp:kompute-regdev
48m 11s
kompute: add backend registry / device interfaces and Q4_K shader CI #16250: Pull request #10045 synchronize by slp
3m 47s slp:kompute-regdev
slp:kompute-regdev
3m 47s
ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the… CI #16249: Commit 8f275a7 pushed by 0cc4m
1h 31m 13s master
master
1h 31m 13s
sampling: add K-Shift sampler CI #16248: Pull request #10048 synchronize by MaggotHATE
1h 8m 10s MaggotHATE:k-shift2
MaggotHATE:k-shift2
1h 8m 10s
llama : remove Tail-Free sampling (#10071) CI #16247: Commit 8d8ff71 pushed by ggerganov
1h 34m 43s master
master
1h 34m 43s
sampling: add K-Shift sampler CI #16246: Pull request #10048 synchronize by MaggotHATE
55m 20s MaggotHATE:k-shift2
MaggotHATE:k-shift2
55m 20s
add FP8 support to gguf/llama: CI #16245: Pull request #10055 synchronize by Djip007
55m 20s Djip007:feature/fp8
Djip007:feature/fp8
55m 20s
add FP8 support to gguf/llama: CI #16243: Pull request #10055 synchronize by Djip007
21m 41s Djip007:feature/fp8
Djip007:feature/fp8
21m 41s
add FP8 support to gguf/llama: CI #16242: Pull request #10055 synchronize by Djip007
8m 43s Djip007:feature/fp8
Djip007:feature/fp8
8m 43s
add FP8 support to gguf/llama: CI #16241: Pull request #10055 synchronize by Djip007
48m 18s Djip007:feature/fp8
Djip007:feature/fp8
48m 18s
add FP8 support to gguf/llama: CI #16240: Pull request #10055 synchronize by Djip007
20m 13s Djip007:feature/fp8
Djip007:feature/fp8
20m 13s
llama : refactor model loader with backend registry CI #16239: Pull request #10026 synchronize by slaren
57m 12s sl/load-time-supports-op
sl/load-time-supports-op
57m 12s
llama : refactor model loader with backend registry CI #16238: Pull request #10026 synchronize by slaren
14m 7s sl/load-time-supports-op
sl/load-time-supports-op
14m 7s
llama : Add IBM granite template (#10013) CI #16237: Commit 61715d5 pushed by ngxson
1h 22m 25s master
master
1h 22m 25s
llama : Add IBM granite template CI #16236: Pull request #10013 synchronize by ngxson
48m 51s master
master
48m 51s
llama : Add IBM granite template CI #16235: Pull request #10013 synchronize by ngxson
1m 29s master
master
1m 29s
llama : Add IBM granite template CI #16234: Pull request #10013 synchronize by arch-btw
1h 41m 28s master
master
1h 41m 28s
llama : Add IBM granite template CI #16233: Pull request #10013 synchronize by arch-btw
12m 37s master
master
12m 37s
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars CI #16232: Pull request #9639 synchronize by ochafik
47m 34s ochafik:tool-call
ochafik:tool-call
47m 34s
sampling: add K-Shift sampler CI #16231: Pull request #10048 synchronize by MaggotHATE
54m 9s MaggotHATE:k-shift2
MaggotHATE:k-shift2
54m 9s
musa: workaround for Guilty Lockup in cleaning src0 (#10042) CI #16230: Commit 524afee pushed by JohannesGaessler
58m 46s master
master
58m 46s
llama : remove Tail-Free sampling CI #16229: Pull request #10071 opened by ggerganov
59m 9s gg/remove-tfs
gg/remove-tfs
59m 9s
server : don't overfill the batch during infill (#10018) CI #16228: Commit 8125e6c pushed by ggerganov
1h 4m 51s master
master
1h 4m 51s