Skip to content

Actions: mudler/vllm.cpp

Actions

containers

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
containers.yml
1,128 workflow runs
1,128 workflow runs

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
fix(BACKEND-TENSTORRENT-KEEPQUANT): correct V-row offset and NaN comparison in keep-quant test containers #3137: Pull request #3189 opened by localai-org-maint-bot
12m 45s row/BACKEND-TENSTORRENT-KEEPQUANT
row/BACKEND-TENSTORRENT-KEEPQUANT
12m 45s
feat(KERNEL-QUANT-CIQ-GEMM-ROCM-RDNA3): enable gfx1100 WMMA prefill containers #3136: Pull request #3187 opened by VikashLoomba
12m 41s VikashLoomba:row/KERNEL-QUANT-CIQ-GEMM-ROCM-RDNA3
VikashLoomba:row/KERNEL-QUANT-CIQ-GEMM-ROCM-RDNA3
12m 41s
docs: correct Qwen3.8-Flash-Next generation claims containers #3135: Pull request #3186 opened by localai-org-maint-bot
12m 28s localai-org-maint-bot:docs/source-alignment-20260914
localai-org-maint-bot:docs/source-alignment-20260914
12m 28s
feat(MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm): run the DeepSeek-V4-Flash-Vision tower on CUDA against llama.cpp b10766 containers #3134: Pull request #3163 synchronize by mudler
13m 8s row/MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm
row/MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm
13m 8s
feat(MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm): run the DeepSeek-V4-Flash-Vision tower on CUDA against llama.cpp b10766 containers #3133: Pull request #3163 synchronize by mudler
12m 38s row/MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm
row/MODEL-MM-deepseek-v4-deepseek-v4-for-causal-lm
12m 38s
fix(MODEL-MM-QWEN4-EXP): guard ManagedAllocActive call with VLLM_CPP_HIP on non-ROCm builds containers #3132: Pull request #3185 synchronize by mudler
36m 56s fix/managed-alloc-active-linker
fix/managed-alloc-active-linker
36m 56s
fix(MODEL-MM-QWEN4-EXP): guard ManagedAllocActive call with VLLM_CPP_HIP on non-ROCm builds containers #3131: Pull request #3185 opened by localai-org-maint-bot
1m 22s fix/managed-alloc-active-linker
fix/managed-alloc-active-linker
1m 22s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3130: Pull request #3183 synchronize by lu-zero
13m 5s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
13m 5s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3129: Pull request #3183 synchronize by lu-zero
8m 20s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
8m 20s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3128: Pull request #3183 synchronize by lu-zero
12m 15s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
12m 15s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3127: Pull request #3183 synchronize by lu-zero
12m 54s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
12m 54s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3126: Pull request #3183 synchronize by lu-zero
12m 0s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
12m 0s
feat(BACKEND-TENSTORRENT-KEEPQUANT): the 27B fits — packed GDN projections, int8-dot captured decode, per-request logits gather (#3042) containers #3125: Pull request #3183 synchronize by lu-zero
7m 25s lu-zero:row/BACKEND-TT-KEEPQUANT-W3
lu-zero:row/BACKEND-TT-KEEPQUANT-W3
7m 25s
spec(MODEL-MM-GLM53-FLASH): W9c-3 compose wave — glm5_next_device.cpp and the remaining eight arms containers #3124: Pull request #3175 synchronize by mudler
36m 8s row/MODEL-MM-GLM53-FLASH-W9C3
row/MODEL-MM-GLM53-FLASH-W9C3
36m 8s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3123: Pull request #3180 synchronize by mudler
44m 28s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
44m 28s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3122: Pull request #3180 synchronize by mudler
2m 22s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
2m 22s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3121: Pull request #3180 synchronize by mudler
14m 10s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
14m 10s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3120: Pull request #3180 synchronize by mudler
13m 50s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
13m 50s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3119: Pull request #3180 synchronize by mudler
3m 8s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
3m 8s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3118: Pull request #3180 synchronize by mudler
2m 49s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
2m 49s
fix: add DeepseekV41ForCausalLM to test_model_loader_gguf expected arch list containers #3117: Pull request #3179 synchronize by mudler
1h 28m 40s fix/test-loader-gguf-arch-list
fix/test-loader-gguf-arch-list
1h 28m 40s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3116: Pull request #3180 synchronize by mudler
10m 0s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
10m 0s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3115: Pull request #3180 synchronize by mudler
20m 32s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
20m 32s
feat(MODEL-MM-QWEN4-EXP): stage a large pageable H2D through a bounded pinned ring on ROCm containers #3114: Pull request #3180 opened by localai-org-maint-bot
9m 12s row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
row/MODEL-MM-QWEN4-EXP-ROCM-CHUNKED-H2D
9m 12s
fix: add DeepseekV41ForCausalLM to test_model_loader_gguf expected arch list containers #3113: Pull request #3179 synchronize by mudler
15m 45s fix/test-loader-gguf-arch-list
fix/test-loader-gguf-arch-list
15m 45s