Mortdecai
eecebe7ef5
Five-lane parallel research pass. Each subdir under tooling/ has its own README indexing downloaded files with verified upstream sources. - google-official/: deepmind-gemma JAX examples, gemma_pytorch scripts, gemma.cpp API server docs, google-gemma/cookbook notebooks, ai.google.dev HTML snapshots, Gemma 3 tech report - huggingface/: 8 gemma-4-* model cards, chat-template .jinja files, tokenizer_config.json, transformers gemma4/ source, launch blog posts, official HF Spaces app.py - inference-frameworks/: vLLM/llama.cpp/MLX/Keras-hub/TGI/Gemini API/Vertex AI comparison, run_commands.sh with 8 working launches, 9 code snippets - gemma-family/: 12 per-variant briefs (ShieldGemma 2, CodeGemma, PaliGemma 2, Recurrent/Data/Med/TxGemma, Embedding/Translate/Function/Dolphin/SignGemma) - fine-tuning/: Unsloth Gemma 4 notebooks, Axolotl YAMLs (incl 26B-A4B MoE), TRL scripts, Google cookbook fine-tune notebooks, recipe-recommendation.md Findings that update earlier CORPUS_* docs are flagged in tooling/README.md (not applied) — notably the new <|turn>/<turn|> prompt format, gemma_pytorch abandonment, gemma.cpp Gemini-API server, transformers AutoModelForMultimodalLM, FA2 head_dim=512 break, 26B-A4B MoE quantization rules, no Gemma 4 tech report PDF yet, no Gemma-4-generation specialized siblings yet. Pre-commit secrets hook bypassed per user authorization — flagged "secrets" are base64 notebook cell outputs and example Ed25519 keys in the HDP agentic-security demo, not real credentials. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
17 lines
776 B
Plaintext
17 lines
776 B
Plaintext
# Source: vllm-project/vllm main branch — vllm/model_executor/models/registry.py
|
|
# Verified 2026-04-18 via GitHub API.
|
|
|
|
# Line 99 (text-only Gemma 4 CausalLM):
|
|
"Gemma4ForCausalLM": ("gemma4", "Gemma4ForCausalLM"),
|
|
|
|
# Line 230 (multimodal Gemma 4: vision + audio + video):
|
|
"Gemma4ForCausalLM": ("gemma4_mm", "Gemma4ForConditionalGeneration"),
|
|
|
|
# The second (_mm) registration maps Gemma4ForCausalLM -> gemma4_mm.Gemma4ForConditionalGeneration,
|
|
# which wires in:
|
|
# - vision_tower (pixel_values, pixel_position_ids)
|
|
# - audio_tower (input_features_padded, input_features_mask) [E2B/E4B only]
|
|
# - video path (pixel_values_videos — decomposed to frames, up to 32 frames @ 70 soft tokens)
|
|
#
|
|
# vLLM dispatches based on whether the HF config has audio_config populated.
|