ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 19:31:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Deepseek MLA Optimizations

Browse Source 
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
Saood Karim
2025-01-28 13:45:18 -06:00
committed by Iwan Kawrakow
parent 6d7b58eade
commit 35246c4e75
3 changed files with 190 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gguf-py/gguf/constants.py
View File

@@ -274,6 +274,8 @@ class MODEL_TENSOR(IntEnum):
ATTN_Q_B = auto()
ATTN_KV_A_MQA = auto()
ATTN_KV_B = auto()
ATTN_K_B = auto()
ATTN_V_B = auto()
ATTN_Q_A_NORM = auto()
ATTN_KV_A_NORM = auto()
FFN_SUB_NORM = auto()
@@ -403,6 +405,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
MODEL_TENSOR.ATTN_Q_B: "blk.{bid}.attn_q_b",
MODEL_TENSOR.ATTN_KV_A_MQA: "blk.{bid}.attn_kv_a_mqa",
MODEL_TENSOR.ATTN_KV_B: "blk.{bid}.attn_kv_b",
MODEL_TENSOR.ATTN_K_B: "blk.{bid}.attn_k_b",
MODEL_TENSOR.ATTN_V_B: "blk.{bid}.attn_v_b",
MODEL_TENSOR.ATTN_Q_A_NORM: "blk.{bid}.attn_q_a_norm",
MODEL_TENSOR.ATTN_KV_A_NORM: "blk.{bid}.attn_kv_a_norm",
MODEL_TENSOR.ATTN_SUB_NORM: "blk.{bid}.attn_sub_norm",
@@ -967,6 +971,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ATTN_Q_B,
MODEL_TENSOR.ATTN_KV_A_MQA,
MODEL_TENSOR.ATTN_KV_B,
MODEL_TENSOR.ATTN_K_B,
MODEL_TENSOR.ATTN_V_B,
MODEL_TENSOR.ATTN_Q_A_NORM,
MODEL_TENSOR.ATTN_KV_A_NORM,
MODEL_TENSOR.ATTN_OUT,