Skip to content

Actions: ggml-org/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
178 workflow run results
178 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: disable q8_0 mmvq on Nvidia Check Pre-Tokenizer Hashes #246: Commit adc8bac pushed by 0cc4m
12m 21s 0cc4m/vulkan-mmq-dp4a-vec
0cc4m/vulkan-mmq-dp4a-vec
12m 21s
convert : parse safetensors directly Check Pre-Tokenizer Hashes #244: Pull request #15667 opened by compilade
30s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
30s
convert : parse safetensors directly Check Pre-Tokenizer Hashes #243: Commit 85edafe pushed by compilade
29s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
29s
convert : parse safetensors directly Check Pre-Tokenizer Hashes #242: Commit 09a558e pushed by compilade
6m 22s compilade/convert-safetensors-parse
compilade/convert-safetensors-parse
6m 22s
nvidia nemotron nano v2 (nemotronh) (#15507) Check Pre-Tokenizer Hashes #241: Commit e8d99dd pushed by gabe-l-hart
31s master
master
31s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #240: Pull request #15507 synchronize by gabe-l-hart
31s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
31s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #239: Pull request #15507 synchronize by gabe-l-hart
32s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
32s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #238: Pull request #15507 synchronize by gabe-l-hart
28m 6s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
28m 6s
model : add grok-2 support Check Pre-Tokenizer Hashes #237: Pull request #15539 synchronize by CISC
39m 13s cisc/grok-2
cisc/grok-2
39m 13s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #236: Pull request #15507 synchronize by gabe-l-hart
1h 45m 24s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
1h 45m 24s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #235: Pull request #15507 synchronize by gabe-l-hart
1h 23m 28s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
1h 23m 28s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #234: Pull request #15507 synchronize by gabe-l-hart
19m 29s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
19m 29s
model : add grok-2 support Check Pre-Tokenizer Hashes #233: Pull request #15539 synchronize by CISC
30m 16s cisc/grok-2
cisc/grok-2
30m 16s
model : jina-embeddings-v3 support Check Pre-Tokenizer Hashes #232: Pull request #13693 synchronize by CISC
46m 12s cisc/jina-embeddings-v3
cisc/jina-embeddings-v3
46m 12s
model : add grok-2 support Check Pre-Tokenizer Hashes #230: Pull request #15539 synchronize by CISC
20m 49s cisc/grok-2
cisc/grok-2
20m 49s
model : add grok-2 support Check Pre-Tokenizer Hashes #229: Pull request #15539 synchronize by CISC
36m 19s cisc/grok-2
cisc/grok-2
36m 19s
fix expert feed forward length and ffn_down concat Check Pre-Tokenizer Hashes #228: Commit 5d4e407 pushed by CISC
11m 5s cisc/grok-2
cisc/grok-2
11m 5s
model : add grok-2 support Check Pre-Tokenizer Hashes #227: Pull request #15539 synchronize by CISC
1h 2m 38s cisc/grok-2
cisc/grok-2
1h 2m 38s
add support for community BPE vocab Check Pre-Tokenizer Hashes #226: Commit 9f86876 pushed by CISC
22m 34s cisc/grok-2
cisc/grok-2
22m 34s
nvidia nemotron nano v2 (nemotronh) Check Pre-Tokenizer Hashes #225: Pull request #15507 synchronize by gabe-l-hart
21m 36s gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
gabe-l-hart:gabe-l-hart/nvidia-nemotron-nano-15409
21m 36s
kv-cache : remove LLAMA_SET_ROWS checks Check Pre-Tokenizer Hashes #220: Commit 61b7fe2 pushed by ggerganov
27m 50s gg/kv-cache-remove-set-rows-checks
gg/kv-cache-remove-set-rows-checks
27m 50s
model : add grok-2 support Check Pre-Tokenizer Hashes #219: Pull request #15539 synchronize by CISC
1m 3s cisc/grok-2
cisc/grok-2
1m 3s
process all expert layers and try cat instead of hstack Check Pre-Tokenizer Hashes #218: Commit c556663 pushed by CISC
30s cisc/grok-2
cisc/grok-2
30s
model : add grok-2 support Check Pre-Tokenizer Hashes #217: Pull request #15539 synchronize by CISC
32s cisc/grok-2
cisc/grok-2
32s
concatenate split tensors and add more metadata Check Pre-Tokenizer Hashes #216: Commit 6b3f775 pushed by CISC
29s cisc/grok-2
cisc/grok-2
29s