]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : support NVFP4 tensors for Gemma4 (#21971)
authorSigbjørn Skjæret <redacted>
Thu, 16 Apr 2026 14:51:47 +0000 (16:51 +0200)
committerGitHub <redacted>
Thu, 16 Apr 2026 14:51:47 +0000 (16:51 +0200)
commitf772f6e434cce0f92e62c662114b50408f89ee79
tree46caf1144e267dca4e43d2ce8cc8436fb097d4f1
parentb572d1ecd62210229e04cdeffd3ae80dd59f0921
model : support NVFP4 tensors for Gemma4 (#21971)

* support nvfp4 tensors for Gemma4

* add wo_s to build_attn

* add wo_s to build_attn

* fix glm4
105 files changed:
src/llama-graph.cpp
src/llama-graph.h
src/models/afmoe.cpp
src/models/apertus.cpp
src/models/arcee.cpp
src/models/arctic.cpp
src/models/baichuan.cpp
src/models/bailingmoe.cpp
src/models/bailingmoe2.cpp
src/models/bert.cpp
src/models/bitnet.cpp
src/models/bloom.cpp
src/models/chameleon.cpp
src/models/chatglm.cpp
src/models/codeshell.cpp
src/models/cogvlm.cpp
src/models/cohere2-iswa.cpp
src/models/command-r.cpp
src/models/dbrx.cpp
src/models/deci.cpp
src/models/deepseek.cpp
src/models/deepseek2.cpp
src/models/dots1.cpp
src/models/dream.cpp
src/models/ernie4-5-moe.cpp
src/models/ernie4-5.cpp
src/models/eurobert.cpp
src/models/exaone-moe.cpp
src/models/exaone.cpp
src/models/exaone4.cpp
src/models/falcon-h1.cpp
src/models/falcon.cpp
src/models/gemma-embedding.cpp
src/models/gemma.cpp
src/models/gemma2-iswa.cpp
src/models/gemma3.cpp
src/models/gemma3n-iswa.cpp
src/models/gemma4-iswa.cpp
src/models/glm4-moe.cpp
src/models/glm4.cpp
src/models/gpt2.cpp
src/models/gptneox.cpp
src/models/granite-hybrid.cpp
src/models/granite.cpp
src/models/grok.cpp
src/models/grovemoe.cpp
src/models/hunyuan-dense.cpp
src/models/hunyuan-moe.cpp
src/models/internlm2.cpp
src/models/jais.cpp
src/models/jais2.cpp
src/models/jamba.cpp
src/models/kimi-linear.cpp
src/models/lfm2.cpp
src/models/llada-moe.cpp
src/models/llada.cpp
src/models/llama-iswa.cpp
src/models/llama.cpp
src/models/maincoder.cpp
src/models/mimo2-iswa.cpp
src/models/minicpm3.cpp
src/models/minimax-m2.cpp
src/models/mistral3.cpp
src/models/modern-bert.cpp
src/models/mpt.cpp
src/models/nemotron-h.cpp
src/models/nemotron.cpp
src/models/neo-bert.cpp
src/models/olmo.cpp
src/models/olmo2.cpp
src/models/olmoe.cpp
src/models/openai-moe-iswa.cpp
src/models/openelm.cpp
src/models/orion.cpp
src/models/paddleocr.cpp
src/models/pangu-embedded.cpp
src/models/phi2.cpp
src/models/phi3.cpp
src/models/plamo.cpp
src/models/plamo2.cpp
src/models/plamo3.cpp
src/models/plm.cpp
src/models/qwen.cpp
src/models/qwen2.cpp
src/models/qwen2moe.cpp
src/models/qwen2vl.cpp
src/models/qwen3.cpp
src/models/qwen35.cpp
src/models/qwen35moe.cpp
src/models/qwen3moe.cpp
src/models/qwen3next.cpp
src/models/qwen3vl-moe.cpp
src/models/qwen3vl.cpp
src/models/refact.cpp
src/models/rnd1.cpp
src/models/seed-oss.cpp
src/models/smallthinker.cpp
src/models/smollm3.cpp
src/models/stablelm.cpp
src/models/starcoder.cpp
src/models/starcoder2.cpp
src/models/step35-iswa.cpp
src/models/t5-dec.cpp
src/models/t5-enc.cpp
src/models/xverse.cpp