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
1,752 workflow runs
1,752 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
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2207: Pull request #22378 synchronize by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2206: Pull request #22378 synchronize by nisparks
-1s nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
-1s
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2205: Pull request #22378 synchronize by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2204: Pull request #22378 synchronize by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2203: Pull request #22378 synchronize by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
Dear devs, please add my model to the list. Thank you. Check Pre-Tokenizer Hashes #2202: Pull request #22380 synchronize by nu11secur1ty
Action required nu11secur1ty:master
nu11secur1ty:master
Action required
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2201: Pull request #22378 synchronize by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
model: add Zamba2 architecture support Check Pre-Tokenizer Hashes #2200: Pull request #21412 synchronize by echo313unfolding
Action required echo313unfolding:zamba2-support
echo313unfolding:zamba2-support
Action required
mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech) Check Pre-Tokenizer Hashes #2199: Pull request #22101 synchronize by ReinforcedKnowledge
24m 58s ReinforcedKnowledge:add-granite-speech-support
ReinforcedKnowledge:add-granite-speech-support
24m 58s
convert : remove input_scale for dequantized fp8 modelopt Check Pre-Tokenizer Hashes #2198: Pull request #22356 synchronize by CISC
1m 1s cisc/convert-modelopt-input-scale-fp8
cisc/convert-modelopt-input-scale-fp8
1m 1s
remove input_scale for dequantized tensors Check Pre-Tokenizer Hashes #2197: Commit fed918a pushed by CISC
59s cisc/convert-modelopt-input-scale-fp8
cisc/convert-modelopt-input-scale-fp8
59s
model: add Zamba2 architecture support Check Pre-Tokenizer Hashes #2196: Pull request #21412 synchronize by echo313unfolding
Action required echo313unfolding:zamba2-support
echo313unfolding:zamba2-support
Action required
Dear devs, please add my model to the list. Thank you. Check Pre-Tokenizer Hashes #2195: Pull request #22380 opened by nu11secur1ty
Action required nu11secur1ty:master
nu11secur1ty:master
Action required
Wip/deepseek v4 support Check Pre-Tokenizer Hashes #2194: Pull request #22378 opened by nisparks
Action required nisparks:wip/deepseek-v4-support
nisparks:wip/deepseek-v4-support
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2193: Pull request #22359 synchronize by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2192: Pull request #22359 synchronize by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2191: Pull request #22359 synchronize by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2190: Pull request #22359 synchronize by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2189: Pull request #22359 synchronize by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
Add DeepSeek V4 GGUF conversion Check Pre-Tokenizer Hashes #2188: Pull request #22359 opened by nisparks
Action required nisparks:experiment/deepseek-v4-gguf-convert
nisparks:experiment/deepseek-v4-gguf-convert
Action required
convert : remove input_scale for dequantized fp8 modelopt Check Pre-Tokenizer Hashes #2187: Pull request #22356 opened by CISC
5m 6s cisc/convert-modelopt-input-scale-fp8
cisc/convert-modelopt-input-scale-fp8
5m 6s
tuple fix Check Pre-Tokenizer Hashes #2186: Commit f730d48 pushed by CISC
15m 18s cisc/convert-modelopt-input-scale-fp8
cisc/convert-modelopt-input-scale-fp8
15m 18s
support input_scale for fp8 modelopt Check Pre-Tokenizer Hashes #2185: Commit 46d4461 pushed by CISC
14m 54s cisc/convert-modelopt-input-scale-fp8
cisc/convert-modelopt-input-scale-fp8
14m 54s
feat: Support sarashina2.2-vision-3b model Check Pre-Tokenizer Hashes #2184: Pull request #22103 synchronize by samuraieng
Action required samuraieng:samuraieng/sarashina22vl-00
samuraieng:samuraieng/sarashina22vl-00
Action required
[Speculative decoding] feat: add DFlash support Check Pre-Tokenizer Hashes #2183: Pull request #22105 synchronize by ruixiang63
Action required ruixiang63:dflash
ruixiang63:dflash
Action required