model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)

* model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Assisted-by: Claude Opus 5.5

* tests : set the SWA rope base of the LFM3 test model

Assisted-by: Claude Opus 5.5

* llama : enable recurrent state rollback for LFM3

Assisted-by: Claude Opus 5.5

* Apply batched suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Tarek Dakhran <github@dakhran.com>

* gguf-py : align the lfm3vl mapping comments

Assisted-by: Claude Opus 5.5

* llama : fix CRLF line endings from the review suggestions

Assisted-by: Claude Opus 5.5

* tests : add the LFM3 Metal fusion baseline

Assisted-by: Claude Opus 5.5

* llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing

Assisted-by: Claude Opus 5.5

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
This commit is contained in:
authored and GitHub committed 2026-10-27 17:06:40 +01:00
1 parent e86f5fd1e9
commit 19cce69199
23 files changed
+1070 -5

No files matched your search

+4
View File
@@ -135,6 +135,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_OPENAI_MOE, "gpt-oss" },
{ LLM_ARCH_LFM2, "lfm2" },
{ LLM_ARCH_LFM2MOE, "lfm2moe" },
{ LLM_ARCH_LFM3, "lfm3" },
{ LLM_ARCH_DREAM, "dream" },
{ LLM_ARCH_SMALLTHINKER, "smallthinker" },
{ LLM_ARCH_LLADA, "llada" },
@@ -1251,6 +1252,7 @@ bool llm_arch_is_hybrid(const llm_arch & arch) {
case LLM_ARCH_GRANITE_HYBRID:
case LLM_ARCH_LFM2:
case LLM_ARCH_LFM2MOE:
case LLM_ARCH_LFM3:
case LLM_ARCH_NEMOTRON_H:
case LLM_ARCH_NEMOTRON_H_MOE:
case LLM_ARCH_QWEN3NEXT:
@@ -1295,6 +1297,7 @@ bool llm_arch_supports_rs_rollback(const llm_arch & arch) {
case LLM_ARCH_NEMOTRON_H_MOE:
case LLM_ARCH_LFM2:
case LLM_ARCH_LFM2MOE:
case LLM_ARCH_LFM3:
case LLM_ARCH_BAILINGMOE3:
return true;
default:
@@ -1341,6 +1344,7 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
case LLM_ARCH_NEMOTRON_H:
case LLM_ARCH_NEMOTRON_H_MOE:
case LLM_ARCH_GRANITE_HYBRID:
case LLM_ARCH_LFM3:
case LLM_ARCH_MINIMAX_01:
case LLM_ARCH_MINIMAX_M2:
case LLM_ARCH_MINIMAX_M3: