Skip to content

Add logging for all prompts to prefill and generate calls #186

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kirklandsign merged 1 commit into from
Jan 27, 2026
Merged

Add logging for all prompts to prefill and generate calls #186

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions ...LlamaDemo/app/src/main/java/com/example/executorchllamademo/ui/viewmodel/ChatViewModel.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,8 +245,9 @@ class ChatViewModel(application: Application) : AndroidViewModel(application), L
modelInfo = "Successfully loaded model. $pteName and tokenizer $tokenizerName in ${loadDuration.toFloat() / 1000} sec. $capabilityText"

if (currentSettingsFields.modelType == ModelType.LLAVA_1_5) {
ETLogging.getInstance().log("Llava start prefill prompt")
module?.prefillPrompt(PromptFormat.getLlavaPresetPrompt())
val llavaPresetPrompt = PromptFormat.getLlavaPresetPrompt()
ETLogging.getInstance().log("Llava start prefill prompt: $llavaPresetPrompt")
module?.prefillPrompt(llavaPresetPrompt)
ETLogging.getInstance().log("Llava completes prefill prompt")
}
loadSuccess = true
Expand Down Expand Up @@ -335,7 +336,9 @@ class ChatViewModel(application: Application) : AndroidViewModel(application), L
ModelUtils.VISION_MODEL_IMAGE_CHANNELS
)
} else if (currentSettingsFields.modelType == ModelType.GEMMA_3) {
module?.prefillPrompt(PromptFormat.getGemmaPreImagePrompt())
val gemmaPreImagePrompt = PromptFormat.getGemmaPreImagePrompt()
ETLogging.getInstance().log("Gemma prefill pre-image prompt: $gemmaPreImagePrompt")
module?.prefillPrompt(gemmaPreImagePrompt)
module?.prefillImages(
img.getFloats(),
img.width,
Expand Down Expand Up @@ -416,8 +419,10 @@ class ChatViewModel(application: Application) : AndroidViewModel(application), L
if (currentSettingsFields.modelType == ModelType.VOXTRAL && audioFileToPrefill != null) {
prefillVoxtralAudio(audioFileToPrefill!!, finalPrompt)
audioFileToPrefill = null
ETLogging.getInstance().log("Running vision model inference.. prompt=(empty after audio prefill)")
module?.generate("", ModelUtils.VISION_MODEL_SEQ_LEN, this, false)
} else {
ETLogging.getInstance().log("Running vision model inference.. prompt=$finalPrompt")
module?.generate(finalPrompt, ModelUtils.VISION_MODEL_SEQ_LEN, this, false)
}
} else if (currentSettingsFields.modelType == ModelType.LLAMA_GUARD_3) {
Expand Down Expand Up @@ -460,9 +465,13 @@ class ChatViewModel(application: Application) : AndroidViewModel(application), L
val bins = 128
val frames = 3000
val batchSize = floatCount / (bins * frames)
module?.prefillPrompt("<s>[INST][BEGIN_AUDIO]")
val preAudioPrompt = "<s>[INST][BEGIN_AUDIO]"
val postAudioPrompt = "$textPrompt[/INST]"
ETLogging.getInstance().log("Voxtral prefill pre-audio prompt: $preAudioPrompt")
module?.prefillPrompt(preAudioPrompt)
module?.prefillAudio(floats, batchSize, bins, frames)
module?.prefillPrompt("$textPrompt[/INST]")
ETLogging.getInstance().log("Voxtral prefill post-audio prompt: $postAudioPrompt")
module?.prefillPrompt(postAudioPrompt)
} catch (e: IOException) {
Log.e("AudioPrefill", "Audio file error")
}
Expand Down