Skip to content

Actions: Nathanw1014/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
453 workflow runs
453 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
ggml-alloc : grow the chunk list on demand instead of an unbounded 16… .github/workflows/build-cann.yml #214: Commit 4a4e1aa pushed by Nathanw1014
Failure hb/alloc-growable-chunks
hb/alloc-growable-chunks
Failure
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 Python check requirements.txt #10: Commit 9e21f2e pushed by Nathanw1014
1d 0h 0m 2s v0.7.8
v0.7.8
1d 0h 0m 2s
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 Copilot Setup Steps #6: Commit 9e21f2e pushed by Nathanw1014
1m 39s v0.7.8
v0.7.8
1m 39s
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 Python Type-Check #44: Commit 9e21f2e pushed by Nathanw1014
1d 0h 0m 1s v0.7.8
v0.7.8
1d 0h 0m 1s
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 Update Operations Documentation #13: Commit 9e21f2e pushed by Nathanw1014
1d 0h 0m 2s v0.7.8
v0.7.8
1d 0h 0m 2s
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 Check Pre-Tokenizer Hashes #13: Commit 9e21f2e pushed by Nathanw1014
1d 0h 0m 1s v0.7.8
v0.7.8
1d 0h 0m 1s
speculative : keep every verify row for MTP accept when another draft… Update Operations Documentation #12: Commit 8e9dcfe pushed by Nathanw1014
1d 0h 0m 2s v0.7.8.1
v0.7.8.1
1d 0h 0m 2s
speculative : keep every verify row for MTP accept when another draft… Check Pre-Tokenizer Hashes #12: Commit 8e9dcfe pushed by Nathanw1014
1d 0h 0m 2s v0.7.8.1
v0.7.8.1
1d 0h 0m 2s
speculative : keep every verify row for MTP accept when another draft… Copilot Setup Steps #5: Commit 8e9dcfe pushed by Nathanw1014
1m 56s v0.7.8.1
v0.7.8.1
1m 56s
speculative : keep every verify row for MTP accept when another draft… Python Type-Check #43: Commit 8e9dcfe pushed by Nathanw1014
1d 0h 0m 22s v0.7.8.1
v0.7.8.1
1d 0h 0m 22s
speculative : keep every verify row for MTP accept when another draft… Python check requirements.txt #9: Commit 8e9dcfe pushed by Nathanw1014
1d 0h 0m 1s v0.7.8.1
v0.7.8.1
1d 0h 0m 1s
qwen4exp: LLAMA_HC_XN_PAD defaults to 128 .github/workflows/build-cann.yml #213: Commit 9e21f2e pushed by Nathanw1014
Failure release/v0.7.8-staging
release/v0.7.8-staging
Failure
speculative : keep every verify row for MTP accept when another draft… .github/workflows/build-cann.yml #212: Commit 8e9dcfe pushed by Nathanw1014
Failure release/v0.7.8.1-staging
release/v0.7.8.1-staging
Failure
speculative : keep every verify row for MTP accept when another draft… Strix Halo release build #55: Commit 8e9dcfe pushed by Nathanw1014
16m 5s strix-halo-vulkan
strix-halo-vulkan
16m 5s
speculative : keep every verify row for MTP accept when another draft… .github/workflows/build-cann.yml #211: Commit 8e9dcfe pushed by Nathanw1014
Failure release/v0.7.8.1-staging
release/v0.7.8.1-staging
Failure
speculative : keep every verify row for MTP accept when another draft… .github/workflows/build-cann.yml #210: Commit 8e9dcfe pushed by Nathanw1014
Failure release/v0.7.8.1-staging
release/v0.7.8.1-staging
Failure
llama : load bf16 matmul weights on GPU buffers as f16 .github/workflows/build-cann.yml #209: Commit 4347f18 pushed by Nathanw1014
Failure strix-halo-vulkan
strix-halo-vulkan
Failure
llama : load bf16 matmul weights on GPU buffers as f16 Strix Halo release build #54: Commit 4347f18 pushed by Nathanw1014
20m 38s strix-halo-vulkan
strix-halo-vulkan
20m 38s
llama : load bf16 matmul weights on GPU buffers as f16 .github/workflows/build-cann.yml #208: Commit 4347f18 pushed by Nathanw1014
Failure strix-halo-vulkan
strix-halo-vulkan
Failure
ggml-alloc : grow the chunk list on demand instead of an unbounded 16… Strix Halo release build #53: Commit d946969 pushed by Nathanw1014
17m 55s strix-halo-vulkan
strix-halo-vulkan
17m 55s
ggml-alloc : grow the chunk list on demand instead of an unbounded 16… .github/workflows/build-cann.yml #207: Commit d946969 pushed by Nathanw1014
Failure fix/kq-mask-tensor-limit
fix/kq-mask-tensor-limit
Failure
ggml-alloc : grow the chunk list on demand instead of an unbounded 16… .github/workflows/build-cann.yml #206: Commit d946969 pushed by Nathanw1014
Failure fix/kq-mask-tensor-limit
fix/kq-mask-tensor-limit
Failure
vulkan: apply the MoE router weights in the int8 MMQ MUL_MAT_ID epilogue .github/workflows/build-cann.yml #205: Commit 30ef039 pushed by Nathanw1014
Failure hb/vk-mmq-moe-epilogue
hb/vk-mmq-moe-epilogue
Failure
vulkan: short-row RMS norm kernel + RMS_NORM_MUL_MUL / RMS_NORM_SCALE… .github/workflows/build-cann.yml #204: Commit 5206263 pushed by Nathanw1014
Failure hb/vk-gdn-conv-norm
hb/vk-gdn-conv-norm
Failure
vulkan : multi-row coopmat1 flash attention for prefill, with a V^T s… .github/workflows/build-cann.yml #203: Commit 304f481 pushed by Nathanw1014
-1s hb/vk-fa-mr
hb/vk-fa-mr
-1s