Skip to content
Closed

Xunchan #11108

Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
File renamed without changes.
File renamed without changes.
2 changes: 1 addition & 1 deletion docs/backend/CANN.md → doc/backend/CANN.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

**Ascend NPU** is a range of AI processors using Neural Processing Unit. It will efficiently handle matrix-matrix multiplication, dot-product and scalars.

**CANN** (Compute Architecture for Neural Networks) is a heterogeneous computing architecture for AI scenarios, providing support for multiple AI frameworks on the top and serving AI processors and programming at the bottom. It plays a crucial role in bridging the gap between upper and lower layers, and is a key platform for improving the computing efficiency of Ascend AI processors. Meanwhile, it offers a highly efficient and easy-to-use programming interface for diverse application scenarios, allowing users to rapidly build AI applications and services based on the Ascend platform.
**CANN** (Compute Architecture for Neural Networks) is a heterogeneous computing architecture for AI scenarios, providing support for multiple AI frameworks on the top and serving AI processors and programming at the bottom. It plays a crucial role in bridging the gap between upper and lower layers, and is a key platform for improving the computing efficiency of Ascend AI processors. Meanwhile, it offers a highly efficient and easy-to-use programming interface for diverse application scenarios, allowing users to rapidly build AI applications and services based on the Alsscend platform.

**Llama.cpp + CANN**

Expand Down
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
4 changes: 4 additions & 0 deletions doc/issue.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
# git

if you modify doc/build.md, you cannot git add it, because it is in .gitignore file

47 changes: 47 additions & 0 deletions doc/story.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
# Complie

doc/build.md

# model

[prithivMLmods/Llama-Deepsync-1B-GGUF](https://huggingface.co/prithivMLmods/Llama-Deepsync-1B-GGUF)

# Run model

./build/bin/llama-cli -m models/Llama-Deepsync-1B.Q4_K_M.gguf -p "what's your name"

# Specific parameter

cd /home/xunchan/Workspace/llama.xunchan/gguf-py/examples

python reader.py /home/xunchan/Workspace/llama.xunchan/models/Llama-Deepsync-1B.Q4_K_M.gguf

or

show in [huggingface](https://huggingface.co/) frontend

## general.architecture

llama

## llama

### llama.block_count

### llama.context_length

### llama.embedding_length

### llama.feed_forward_length

###

#### block

# Modify code

## Find the llama block code process location

## Write it precifily

##
Loading