mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

arch: refactor LLM_TENSOR_NAMES (#18051)

Browse Source 
* arch: refactor LLM_TENSOR_NAMES

* update docs

* typo

* fix LLM_ARCH_NEMOTRON_H_MOE

* show more meaningful error message on missing tensor

* fix and tested LLM_ARCH_NEMOTRON_H_MOE
This commit is contained in:
Xuan-Son Nguyen
2025-12-16 13:22:30 +01:00
committed by GitHub
parent 7b1db3d3b7
commit 7f2b2f3c77
3 changed files with 1897 additions and 2284 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+1888 -2281
View File
File diff suppressed because it is too large Load Diff
src/llama-arch.h
+8 -2
View File
@@ -3,6 +3,7 @@
#include "ggml.h" // ggml_op
#include <string>
#include <set>
//
// gguf constants (sync with gguf.py)
@@ -316,6 +317,7 @@ enum llm_tensor {
LLM_TENSOR_DENSE_3_OUT,
LLM_TENSOR_OUTPUT,
LLM_TENSOR_OUTPUT_NORM,
LLM_TENSOR_OUTPUT_NORM_LFM2, // fix for wrong tensor name
LLM_TENSOR_ROPE_FREQS,
LLM_TENSOR_ROPE_FACTORS_LONG,
LLM_TENSOR_ROPE_FACTORS_SHORT,
@@ -526,6 +528,10 @@ struct LLM_TN_IMPL {
const int bid;
const int xid;
const std::set<llm_tensor> model_tensors;
LLM_TN_IMPL(llm_arch arch, llm_tensor tensor, const char * suffix, int bid, int xid);
std::string str() const;
operator std::string() const {
@@ -547,11 +553,11 @@ struct LLM_TN {
llm_arch arch;
LLM_TN_IMPL operator()(llm_tensor tensor, const char * suffix, int bid = -1, int xid = -1) const {
return { arch, tensor, suffix, bid, xid };
return LLM_TN_IMPL(arch, tensor, suffix, bid, xid);
}
LLM_TN_IMPL operator()(llm_tensor tensor, int bid = -1, int xid = -1) const {
return { arch, tensor, nullptr, bid, xid };
return LLM_TN_IMPL(arch, tensor, nullptr, bid, xid);
}
};