Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

TP: enable tensor split for LFM2/LFM2MOE (#26993)

Browse Source 
Assisted-by: deepseek-v4-flash
This commit is contained in:
Chris Danis
2026-08-21 08:13:58 +03:00
committed by GitHub
parent a298422da7
commit b2e5e9b28b
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
-2
View File
@@ -1062,8 +1062,6 @@ 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_LFM2:
case LLM_ARCH_LFM2MOE:
case LLM_ARCH_MINIMAX_01:
case LLM_ARCH_MINIMAX_M2:
case LLM_ARCH_MINIMAX_M3: