v1.9.0 (#50)

ngxson · May 18, 2024 · 454c5ed · 454c5ed
1 parent 25dd0cd
commit 454c5ed
Show file tree

Hide file tree

Showing 7 changed files with 10 additions and 9 deletions.
diff --git a/README.md b/README.md
@@ -6,18 +6,19 @@ Another WebAssembly binding for [llama.cpp](https://github.com/ggerganov/llama.c
 
 ## Recent changes
 
+- Version 1.9.0
+  - Added custom logger
+  - Added `getModelMetadata()`
+  - Added support for EOT (end of turn) and `stopTokens` in `createCompletion()`
 - Version 1.8.0
   - Docs & demo address changed from `ngxson.github.io` to `github.ngxson.com`. This allows adding COOP/COEP headers (required to run multi-thread examples)
   - Added `abortSignal`, see [#26](https://github.com/ngxson/wllama/pull/26)
   - For more details, see [releases page](https://github.com/ngxson/wllama/releases)
 - Version 1.7.0
   - When downloading, `n_downloads_parallel` is changed to `parallelDownloads`
   - Added support for `progressCallback` when downloading. See [advanced example](./examples/advanced/index.html)
-- Version 1.5.0
-  - Support split model using [gguf-split tool](https://github.com/ggerganov/llama.cpp/tree/master/examples/gguf-split)
-- Version 1.4.0
-  - Add `single-thread/wllama.js` and `multi-thread/wllama.js` to the list of `CONFIG_PATHS`
-  - `createEmbedding` is now adding BOS and EOS token by default
+
+For more details, see [releases](https://github.com/ngxson/wllama/releases)
 
 ## Features
 

diff --git a/llama.cpp b/llama.cpp
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@wllama/wllama",
-  "version": "1.8.1",
+  "version": "1.9.0",
   "description": "Low-level WASM binding for llama.cpp",
   "main": "index.js",
   "type": "module",

diff --git a/src/multi-thread/wllama.js b/src/multi-thread/wllama.js
diff --git a/src/multi-thread/wllama.wasm b/src/multi-thread/wllama.wasm
diff --git a/src/single-thread/wllama.js b/src/single-thread/wllama.js
diff --git a/src/single-thread/wllama.wasm b/src/single-thread/wllama.wasm
+8 −8		.devops/nix/package.nix
+73 −0		.github/labeler.yml
+58 −0		.github/workflows/build.yml
+12 −0		.github/workflows/labeler.yml
+34 −8		CMakeLists.txt
+3 −3		Makefile
+19 −6		README.md
+1 −1		common/common.cpp
+37 −46		convert-hf-to-gguf-update.py
+18 −12		convert-hf-to-gguf.py
+20 −4		docs/debugging-tests.md
+2 −2		examples/perplexity/perplexity.cpp
+4 −0		examples/rpc/rpc-server.cpp
+4 −5		examples/server/README.md
+7 −8		examples/server/bench/bench.py
+7 −0		examples/server/server.cpp
+14 −0		ggml-cuda/common.cuh
+395 −0		ggml-cuda/fattn-tile-f16.cu
+3 −0		ggml-cuda/fattn-tile-f16.cuh
+393 −0		ggml-cuda/fattn-tile-f32.cu
+3 −0		ggml-cuda/fattn-tile-f32.cuh
+3 −6		ggml-cuda/fattn-vec-f16.cu
+3 −6		ggml-cuda/fattn-vec-f32.cu
+23 −3		ggml-cuda/fattn.cu
+19 −13		ggml-quants.c
+11 −2		ggml-rpc.cpp
+1,043 −1,028		ggml-vulkan-shaders.hpp
+65 −129		ggml-vulkan.cpp
+283 −193		ggml.c
+59 −27		ggml_vk_generate_shaders.py
+33 −15		llama.cpp
+176 −90		scripts/debug-test.sh
+116 −46		scripts/gen-unicode-data.py
+18 −0		tests/test-backend-ops.cpp
+60 −53		tests/test-tokenizer-random.py
+6,969 −2,169		unicode-data.cpp
+15 −12		unicode-data.h
+89 −111		unicode.cpp
+44 −12		unicode.h