Skip to content

Actions: mudler/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
31 workflow runs
31 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
test(paged): P1 bf16-stream BF16_STREAM_SEGMENT sentinel .github/workflows/build-cann.yml #6: Commit 653bb2f pushed by mudler
Failure localai-paged
localai-paged
Failure
feat(paged): whole-pattern MoE matcher + routed-FFN fused NVFP4-quant… .github/workflows/build-cann.yml #5: Commit 1edddc8 pushed by mudler
Failure localai-paged
localai-paged
Failure
feat(paged): fused gated RMSNorm + SiLU gate-mul CUDA op (patch 0044) .github/workflows/build-cann.yml #4: Commit 51168c5 pushed by mudler
Failure localai-paged
localai-paged
Failure
feat(paged): GDN M5 tensor-core chunked-scan prefill, f32-only re-por… .github/workflows/build-cann.yml #3: Commit 2c32ab8 pushed by mudler
Failure localai-paged
localai-paged
Failure
feat(paged): gate GDN prefill geometry by scan length (patch 0046) Update Operations Documentation #4: Commit dc010d6 pushed by mudler
1d 0h 0m 2s localai-paged
localai-paged
1d 0h 0m 2s
feat(paged): gate GDN prefill geometry by scan length (patch 0046) Python check requirements.txt #7: Commit dc010d6 pushed by mudler
1d 0h 0m 1s localai-paged
localai-paged
1d 0h 0m 1s
feat(paged): gate GDN prefill geometry by scan length (patch 0046) Check Pre-Tokenizer Hashes #6: Commit dc010d6 pushed by mudler
1d 0h 0m 2s localai-paged
localai-paged
1d 0h 0m 2s
feat(paged): gate GDN prefill geometry by scan length (patch 0046) Python Type-Check #7: Commit dc010d6 pushed by mudler
1d 0h 0m 1s localai-paged
localai-paged
1d 0h 0m 1s
feat(paged): gate GDN prefill geometry by scan length (patch 0046) .github/workflows/build-cann.yml #2: Commit dc010d6 pushed by mudler
Failure localai-paged
localai-paged
Failure
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper Update Operations Documentation #3: Commit 5c537be pushed by mudler
1d 0h 0m 3s fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
1d 0h 0m 3s
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper Check Pre-Tokenizer Hashes #5: Commit 5c537be pushed by mudler
1d 0h 0m 2s fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
1d 0h 0m 2s
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper Python Type-Check #6: Commit 5c537be pushed by mudler
1d 0h 0m 3s fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
1d 0h 0m 3s
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper Python check requirements.txt #6: Commit 5c537be pushed by mudler
1d 0h 0m 3s fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
1d 0h 0m 3s
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper .github/workflows/build-sycl.yml #1: Commit 5c537be pushed by mudler
Failure fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
Failure
mtmd: fix double-close of ffmpeg/ffprobe stdin in video helper .github/workflows/build-cann.yml #1: Commit 5c537be pushed by mudler
Failure fix/mtmd-video-stdin-double-close
fix/mtmd-video-stdin-double-close
Failure
imatrix: optionally activate MTP/NextN draft head during collection Update Operations Documentation #2: Commit fafe7ea pushed by mudler
1m 53s mtp-imatrix
mtp-imatrix
1m 53s
imatrix: optionally activate MTP/NextN draft head during collection Python Type-Check #5: Commit fafe7ea pushed by mudler
3m 52s mtp-imatrix
mtp-imatrix
3m 52s
imatrix: optionally activate MTP/NextN draft head during collection Check Pre-Tokenizer Hashes #4: Commit fafe7ea pushed by mudler
2m 7s mtp-imatrix
mtp-imatrix
2m 7s
imatrix: optionally activate MTP/NextN draft head during collection Python check requirements.txt #5: Commit fafe7ea pushed by mudler
7m 21s mtp-imatrix
mtp-imatrix
7m 21s
memory: respect unified KV cache in hybrid memory for eval tasks Python Type-Check #4: Commit 27ce378 pushed by mudler
4m 22s fix/hybrid-memory-unified-kv
fix/hybrid-memory-unified-kv
4m 22s
memory: respect unified KV cache in hybrid memory for eval tasks Check Pre-Tokenizer Hashes #3: Commit 27ce378 pushed by mudler
4m 49s fix/hybrid-memory-unified-kv
fix/hybrid-memory-unified-kv
4m 49s
memory: respect unified KV cache in hybrid memory for eval tasks Python check requirements.txt #4: Commit 27ce378 pushed by mudler
9m 15s fix/hybrid-memory-unified-kv
fix/hybrid-memory-unified-kv
9m 15s
feat: add TurboQuant support Check Pre-Tokenizer Hashes #2: Commit 6abff46 pushed by mudler
54s feat/turbo-quant
feat/turbo-quant
54s
feat: add TurboQuant support Python check requirements.txt #3: Commit 6abff46 pushed by mudler
6m 2s feat/turbo-quant
feat/turbo-quant
6m 2s
feat: add TurboQuant support Copilot Setup Steps #2: Commit 6abff46 pushed by mudler
1m 58s feat/turbo-quant
feat/turbo-quant
1m 58s