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

spec : auto-detect mtp draft model type (#27005)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2026-08-13 13:39:16 +02:00
committed by GitHub
parent 4a84b0ad10
commit 1d2869c6e5
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/speculative.cpp
+6
View File
@@ -2246,6 +2246,12 @@ std::vector<common_speculative_type> common_speculative_types_from_gguf(const st
const std::string arch = gguf_get_val_str(gguf_ctx.get(), arch_id); const std::string arch = gguf_get_val_str(gguf_ctx.get(), arch_id);
if (arch != "dflash") { if (arch != "dflash") {
const uint32_t block_count = gguf_get_val_u32(gguf_ctx.get(), gguf_find_key(gguf_ctx.get(), (arch + ".block_count").c_str()));
if (gguf_find_tensor(gguf_ctx.get(), ("blk." + std::to_string(block_count - 1) + ".nextn.eh_proj.weight").c_str()) >= 0) {
return { COMMON_SPECULATIVE_TYPE_DRAFT_MTP };
}
return {}; return {};
} }