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
502 workflow run results
502 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Model: Minimax M2 Check Pre-Tokenizer Hashes #634: Pull request #16831 synchronize by pwilkin
57s pwilkin:minimax-m2
pwilkin:minimax-m2
57s
Model: Minimax M2 Check Pre-Tokenizer Hashes #633: Pull request #16831 synchronize by pwilkin
55s pwilkin:minimax-m2
pwilkin:minimax-m2
55s
Model: Minimax M2 Check Pre-Tokenizer Hashes #632: Pull request #16831 synchronize by pwilkin
1m 0s pwilkin:minimax-m2
pwilkin:minimax-m2
1m 0s
Model: Minimax M2 Check Pre-Tokenizer Hashes #631: Pull request #16831 synchronize by pwilkin
3m 27s pwilkin:minimax-m2
pwilkin:minimax-m2
3m 27s
Add mxfp4 mmq, enable MMQ MUL_MAT_ID Check Pre-Tokenizer Hashes #630: Commit 40d75d9 pushed by 0cc4m
1h 18m 22s 0cc4m/vulkan-mmq-dp4a-k-quants
0cc4m/vulkan-mmq-dp4a-k-quants
1h 18m 22s
metal : fix check for bfloat tensor support Check Pre-Tokenizer Hashes #627: Commit f2927f4 pushed by ggerganov
1h 21m 11s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
1h 21m 11s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #626: Pull request #16574 synchronize by pockers21
35m 15s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
35m 15s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #625: Pull request #16574 synchronize by pockers21
29m 9s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
29m 9s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #624: Pull request #16574 synchronize by pockers21
23m 20s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
23m 20s
llama : update per-seq context computation Check Pre-Tokenizer Hashes #623: Commit 3be59c6 pushed by ggerganov
5m 6s gg/server-unified-slots
gg/server-unified-slots
5m 6s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #622: Pull request #16574 synchronize by pockers21
51s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
51s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #621: Pull request #16574 synchronize by pockers21
17m 0s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
17m 0s
support GLM-4.5V and GLM-4.1V vision models Check Pre-Tokenizer Hashes #620: Pull request #16600 synchronize by ddh0
54s ddh0:glm45v-2
ddh0:glm45v-2
54s
model : add LightOnOCR-1B model (#16764) Check Pre-Tokenizer Hashes #619: Commit c55d53a pushed by ngxson
1h 21m 46s master
master
1h 21m 46s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #618: Pull request #16574 synchronize by pockers21
31m 51s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
31m 51s
model : add LightOnOCR-1B model Check Pre-Tokenizer Hashes #617: Pull request #16764 synchronize by ngxson
30m 11s ngxson:xsn/lighton-ocr
ngxson:xsn/lighton-ocr
30m 11s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #616: Pull request #16574 synchronize by pockers21
58s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
58s
support GLM-4.5V and GLM-4.1V vision models Check Pre-Tokenizer Hashes #615: Pull request #16600 synchronize by ddh0
1m 4s ddh0:glm45v-2
ddh0:glm45v-2
1m 4s
convert : enable expert group selection for all models with it (#16691) Check Pre-Tokenizer Hashes #614: Commit 73a48c9 pushed by CISC
6m 7s master
master
6m 7s
[model] add support for qwen3vl series Check Pre-Tokenizer Hashes #613: Pull request #16780 opened by JJJYmmm
7m 28s JJJYmmm:add_qwen3vl
JJJYmmm:add_qwen3vl
7m 28s
model : add PaddleOCR Check Pre-Tokenizer Hashes #612: Pull request #16701 synchronize by ngxson
59s ngxson:xsn/paddleocr
ngxson:xsn/paddleocr
59s
model : add PaddleOCR Check Pre-Tokenizer Hashes #611: Pull request #16701 synchronize by ngxson
1m 5s ngxson:xsn/paddleocr
ngxson:xsn/paddleocr
1m 5s
model : add PaddleOCR Check Pre-Tokenizer Hashes #610: Pull request #16701 synchronize by ngxson
59s ngxson:xsn/paddleocr
ngxson:xsn/paddleocr
59s
convert : handle mmproj filename/path properly (#16760) Check Pre-Tokenizer Hashes #609: Commit 5d195f1 pushed by CISC
57s master
master
57s
convert: Handle mmproj model output filename properly Check Pre-Tokenizer Hashes #608: Pull request #16760 synchronize by Galunid
56s Galunid:fix-mmproj-filename
Galunid:fix-mmproj-filename
56s