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
548 workflow run results
548 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

implement "auto" mode for clip flash attn Check Pre-Tokenizer Hashes #688: Commit b4955f0 pushed by ngxson
16m 3s gg/clip-fa
gg/clip-fa
16m 3s
context : do not cap the size of the context Check Pre-Tokenizer Hashes #687: Commit c08d0d1 pushed by ggerganov
32s gg/server-unified-slots
gg/server-unified-slots
32s
device tuning Check Pre-Tokenizer Hashes #686: Commit d2f8f00 pushed by 0cc4m
33s 0cc4m/vulkan-mmq-dp4a-vec-k-quants
0cc4m/vulkan-mmq-dp4a-vec-k-quants
33s
support GLM-4.5V and GLM-4.1V vision models Check Pre-Tokenizer Hashes #685: Pull request #16600 synchronize by ddh0
23m 35s ddh0:glm45v-2
ddh0:glm45v-2
23m 35s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #684: Pull request #16095 synchronize by pwilkin
10m 17s pwilkin:qwen3_next
pwilkin:qwen3_next
10m 17s
model : Minimax M2 (#16831) Check Pre-Tokenizer Hashes #683: Commit 0de0a01 pushed by CISC
2m 22s master
master
2m 22s
Model: Minimax M2 Check Pre-Tokenizer Hashes #682: Pull request #16831 synchronize by pwilkin
1h 29m 58s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 29m 58s
Model: Minimax M2 Check Pre-Tokenizer Hashes #681: Pull request #16831 synchronize by pwilkin
1h 43m 52s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 43m 52s
Model: Minimax M2 Check Pre-Tokenizer Hashes #680: Pull request #16831 synchronize by pwilkin
1h 42m 30s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 42m 30s
Model: Minimax M2 Check Pre-Tokenizer Hashes #679: Pull request #16831 synchronize by pwilkin
1h 29m 50s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 29m 50s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #678: Pull request #16574 synchronize by pockers21
1h 3m 1s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
1h 3m 1s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #677: Pull request #16574 synchronize by pockers21
39m 25s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
39m 25s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #676: Pull request #16574 synchronize by pockers21
22m 35s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
22m 35s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #675: Pull request #16574 synchronize by pockers21
7m 46s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
7m 46s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #674: Pull request #16574 synchronize by pockers21
1m 34s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
1m 34s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #673: Pull request #16574 synchronize by pockers21
35s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
35s
Model: Minimax M2 Check Pre-Tokenizer Hashes #671: Pull request #16831 synchronize by pwilkin
1h 43m 44s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 43m 44s
Model: Minimax M2 Check Pre-Tokenizer Hashes #672: Pull request #16831 reopened by pwilkin
1h 50m 26s pwilkin:minimax-m2
pwilkin:minimax-m2
1h 50m 26s
support GLM-4.5V and GLM-4.1V vision models Check Pre-Tokenizer Hashes #670: Pull request #16600 synchronize by ddh0
2h 11m 45s ddh0:glm45v-2
ddh0:glm45v-2
2h 11m 45s
Modern Bert Support Check Pre-Tokenizer Hashes #669: Pull request #15641 synchronize by ryan-mangeno
1h 18m 33s ryan-mangeno:modern-bert-support
ryan-mangeno:modern-bert-support
1h 18m 33s
server : support unified context across slots Check Pre-Tokenizer Hashes #668: Commit 0ba88d3 pushed by ggerganov
2h 12m 54s gg/server-unified-slots
gg/server-unified-slots
2h 12m 54s
cont : add warning about unsupported ops Check Pre-Tokenizer Hashes #667: Commit 7ffaf90 pushed by ggerganov
1h 20m 11s gg/clip-fa
gg/clip-fa
1h 20m 11s
model: add support for qwen3vl series (#16780) Check Pre-Tokenizer Hashes #666: Commit d261223 pushed by ngxson
21m 18s master
master
21m 18s
server : fix pos_next() usage Check Pre-Tokenizer Hashes #665: Commit ef1646e pushed by ggerganov
17m 37s gg/server-fix-n-past
gg/server-fix-n-past
17m 37s
Revert "memory : move the recurrent state into the memory context" Check Pre-Tokenizer Hashes #664: Commit 1c241e0 pushed by ggerganov
41m 26s gg/graph-mamba-reuse
gg/graph-mamba-reuse
41m 26s