Merge branch 'master' into hkvc_chat_interactivespecials

Merge master has of 20240510IST1236 into this branch.

Fix a merge conflict with the newly added conversation flag
in master branch.

Author: hanishkvc

CMakeLists.txt

@@ -103,6 +103,8 @@ set(LLAMA_CUDA_KQUANTS_ITER "2" CACHE STRING "llama: iters./thread per block for
 set(LLAMA_CUDA_PEER_MAX_BATCH_SIZE "128" CACHE STRING
                                              "llama: max. batch size for using peer access")
 option(LLAMA_CUDA_NO_PEER_COPY               "llama: do not use peer to peer copies"            OFF)
+option(LLAMA_CUDA_NO_VMM                     "llama: do not try to use CUDA VMM"                OFF)
+
 option(LLAMA_CURL                            "llama: use libcurl to download model from an URL" OFF)
 option(LLAMA_HIPBLAS                         "llama: use hipBLAS"                               OFF)
 option(LLAMA_HIP_UMA                         "llama: use HIP unified memory architecture"       OFF)
@@ -403,12 +405,16 @@ if (LLAMA_CUDA)
         list(APPEND GGML_SOURCES_CUDA "ggml-cuda.cu")
 
         add_compile_definitions(GGML_USE_CUDA)
+        add_compile_definitions(GGML_CUDA_USE_GRAPHS)
         if (LLAMA_CUDA_FORCE_DMMV)
             add_compile_definitions(GGML_CUDA_FORCE_DMMV)
         endif()
         if (LLAMA_CUDA_FORCE_MMQ)
             add_compile_definitions(GGML_CUDA_FORCE_MMQ)
         endif()
+        if (LLAMA_CUDA_NO_VMM)
+            add_compile_definitions(GGML_CUDA_NO_VMM)
+        endif()
         add_compile_definitions(GGML_CUDA_DMMV_X=${LLAMA_CUDA_DMMV_X})
         add_compile_definitions(GGML_CUDA_MMV_Y=${LLAMA_CUDA_MMV_Y})
         if (DEFINED LLAMA_CUDA_DMMV_Y)
@@ -425,7 +431,7 @@ if (LLAMA_CUDA)
 
         if (LLAMA_STATIC)
             if (WIN32)
-                # As of 12.3.1 CUDA Tookit for Windows does not offer a static cublas library
+                # As of 12.3.1 CUDA Toolkit for Windows does not offer a static cublas library
                 set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
             else ()
                 set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
@@ -434,7 +440,11 @@ if (LLAMA_CUDA)
             set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
         endif()
 
-        set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cuda_driver)
+        if (LLAMA_CUDA_NO_VMM)
+            # No VMM requested, no need to link directly with the cuda driver lib (libcuda.so)
+        else()
+            set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
+        endif()
 
     if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
         # 52 == lowest CUDA 12 standard

Makefile

@@ -433,7 +433,7 @@ ifdef LLAMA_CUDA
 	else
 		CUDA_PATH ?= /usr/local/cuda
 	endif
-	MK_CPPFLAGS  += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include
+	MK_CPPFLAGS  += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include -DGGML_CUDA_USE_GRAPHS
 	MK_LDFLAGS   += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L$(CUDA_PATH)/lib64 -L/usr/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib -L/usr/lib/wsl/lib
 	OBJS         += ggml-cuda.o
 	OBJS         += $(patsubst %.cu,%.o,$(wildcard ggml-cuda/*.cu))

README.md

@@ -2,7 +2,7 @@
 
 ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)
 
-[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Server](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml/badge.svg?branch=master&event=schedule)](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml)
 
 [Roadmap](https://github.com/users/ggerganov/projects/7) / [Project status](https://github.com/ggerganov/llama.cpp/discussions/3471) / [Manifesto](https://github.com/ggerganov/llama.cpp/discussions/205) / [ggml](https://github.com/ggerganov/ggml)
 
@@ -20,7 +20,8 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
 
 ### Hot topics
 
-- **BPE pre-tokenization support has been added: https://github.com/ggerganov/llama.cpp/pull/6920**
+- **Initial Flash-Attention support: https://github.com/ggerganov/llama.cpp/pull/5021**
+- BPE pre-tokenization support has been added: https://github.com/ggerganov/llama.cpp/pull/6920
 - MoE memory layout has been updated - reconvert models for `mmap` support and regenerate `imatrix` https://github.com/ggerganov/llama.cpp/pull/6387
 - Model sharding instructions using `gguf-split` https://github.com/ggerganov/llama.cpp/discussions/6404
 - Fix major bug in Metal batched inference https://github.com/ggerganov/llama.cpp/pull/6225
@@ -175,6 +176,7 @@ Unless otherwise noted these projects are open-source with permissive licensing:
 - [nat/openplayground](https://github.com/nat/openplayground)
 - [Faraday](https://faraday.dev/) (proprietary)
 - [LMStudio](https://lmstudio.ai/) (proprietary)
+- [Layla](https://play.google.com/store/apps/details?id=com.laylalite) (proprietary)
 - [LocalAI](https://github.com/mudler/LocalAI) (MIT)
 - [LostRuins/koboldcpp](https://github.com/LostRuins/koboldcpp) (AGPL)
 - [Mozilla-Ocho/llamafile](https://github.com/Mozilla-Ocho/llamafile)
@@ -712,7 +714,7 @@ Building the program with BLAS support may lead to some performance improvements
 
 To obtain the official LLaMA 2 weights please see the <a href="#obtaining-and-using-the-facebook-llama-2-model">Obtaining and using the Facebook LLaMA 2 model</a> section. There is also a large selection of pre-quantized `gguf` models available on Hugging Face.
 
-Note: `convert.py` does not support LLaMA 3, you can use `convert-hf-to-gguf.py` with LLaMA 3 downloaded from Hugging Face. 
+Note: `convert.py` does not support LLaMA 3, you can use `convert-hf-to-gguf.py` with LLaMA 3 downloaded from Hugging Face.
 
 ```bash
 # obtain the official LLaMA model weights and place them in ./models
@@ -935,25 +937,35 @@ If your issue is with model generation quality, then please at least scan the fo
 
 ### Android
 
-#### Building the Project using Android NDK
-You can easily run `llama.cpp` on Android device with [termux](https://termux.dev/).
+#### Build on Android using Termux
+[Termux](https://github.com/termux/termux-app#installation) is a method to execute `llama.cpp` on an Android device (no root required).
+```
+apt update && apt upgrade -y
+apt install git make cmake
+```
 
-First, install the essential packages for termux:
+It's recommended to move your model inside the `~/` directory for best performance:
 ```
-pkg install clang wget git cmake
+cd storage/downloads
+mv model.gguf ~/
 ```
-Second, obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake:
 
-You can execute the following commands on your computer to avoid downloading the NDK to your mobile. Of course, you can also do this in Termux.
+[Get the code](https://github.com/ggerganov/llama.cpp#get-the-code) & [follow the Linux build instructions](https://github.com/ggerganov/llama.cpp#build) to build `llama.cpp`.
+
+#### Building the Project using Android NDK
+Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
 
+Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
 ```
 $ mkdir build-android
 $ cd build-android
 $ export NDK=<your_ndk_directory>
 $ cmake -DCMAKE_TOOLCHAIN_FILE=$NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-23 -DCMAKE_C_FLAGS=-march=armv8.4a+dotprod ..
 $ make
 ```
-Install [termux](https://termux.dev/) on your device and run `termux-setup-storage` to get access to your SD card.
+
+Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice).
+
 Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission:
 
 (Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
@@ -975,25 +987,10 @@ $cd /data/data/com.termux/files/home/bin
 $./main -m ../model/llama-2-7b-chat.Q4_K_M.gguf -n 128 -cml
 ```
 
-Here is a demo of an interactive session running on Pixel 5 phone:
+Here's a demo of an interactive session running on Pixel 5 phone:
 
 https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4
 
-#### Build on Android using Termux
-[Termux](https://github.com/termux/termux-app#installation) is an alternative to execute `llama.cpp` on an Android device (no root required).
-```
-apt update && apt upgrade -y
-apt install git
-```
-
-It's recommended to move your model inside the `~/` directory for best performance:
-```
-cd storage/downloads
-mv model.gguf ~/
-```
-
-[Follow the Linux build instructions](https://github.com/ggerganov/llama.cpp#build) to build `llama.cpp`.
-
 ### Docker
 
 #### Prerequisites

ci/run.sh

@@ -160,9 +160,8 @@ function gg_run_test_scripts_debug {
 
     set -e
 
-    # TODO: too slow, run on dedicated node
-   #(cd ./examples/gguf-split && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
-   #(cd ./examples/quantize   && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
+    (cd ./examples/gguf-split && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
+    (cd ./examples/quantize   && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
 
     set +e
 }
@@ -695,8 +694,10 @@ test $ret -eq 0 && gg_run ctest_release
 if [ -z ${GG_BUILD_LOW_PERF} ]; then
     test $ret -eq 0 && gg_run embd_bge_small
 
-    test $ret -eq 0 && gg_run test_scripts_debug
-    test $ret -eq 0 && gg_run test_scripts_release
+    if [ -z ${GG_BUILD_CLOUD} ] || [ ${GG_BUILD_EXTRA_TESTS_0} ]; then
+        test $ret -eq 0 && gg_run test_scripts_debug
+        test $ret -eq 0 && gg_run test_scripts_release
+    fi
 
     if [ -z ${GG_BUILD_VRAM_GB} ] || [ ${GG_BUILD_VRAM_GB} -ge 8 ]; then
         if [ -z ${GG_BUILD_CUDA} ]; then

common/common.cpp

@@ -1,4 +1,6 @@
 #include "common.h"
+// Change JSON_ASSERT from assert() to GGML_ASSERT:
+#define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
 #include "json-schema-to-grammar.h"
 #include "llama.h"
@@ -915,6 +917,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.instruct = true;
         return true;
     }
+    if (arg == "-cnv" || arg == "--conversation") {
+        params.conversation = true;
+        return true;
+    }
     if (arg == "-cml" || arg == "--chatml") {
         params.chatml = true;
         return true;
@@ -1422,6 +1428,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  -i, --interactive     run in interactive mode\n");
     printf("  --interactive-specials allow special tokens in user text, in interactive mode\n");
     printf("  --interactive-first   run in interactive mode and wait for input right away\n");
+    printf("  -cnv, --conversation  run in conversation mode (does not print special tokens and suffix/prefix)\n");
     printf("  -ins, --instruct      run in instruction mode (use with Alpaca models)\n");
     printf("  -cml, --chatml        run in chatml mode (use with ChatML-compatible models)\n");
     printf("  --multiline-input     allows you to write or paste multiple lines without ending each in '\\'\n");
@@ -1969,18 +1976,18 @@ static bool llama_download_file(const std::string & url, const std::string & pat
             try {
                 metadata_in >> metadata;
                 fprintf(stderr, "%s: previous metadata file found %s: %s\n", __func__, metadata_path.c_str(), metadata.dump().c_str());
-                if (metadata.contains("url") && metadata["url"].is_string()) {
-                    auto previous_url = metadata["url"].get<std::string>();
+                if (metadata.contains("url") && metadata.at("url").is_string()) {
+                    auto previous_url = metadata.at("url").get<std::string>();
                     if (previous_url != url) {
                         fprintf(stderr, "%s: Model URL mismatch: %s != %s\n", __func__, url.c_str(), previous_url.c_str());
                         return false;
                     }
                 }
-                if (metadata.contains("etag") && metadata["etag"].is_string()) {
-                    etag = metadata["etag"];
+                if (metadata.contains("etag") && metadata.at("etag").is_string()) {
+                    etag = metadata.at("etag");
                 }
-                if (metadata.contains("lastModified") && metadata["lastModified"].is_string()) {
-                    last_modified = metadata["lastModified"];
+                if (metadata.contains("lastModified") && metadata.at("lastModified").is_string()) {
+                    last_modified = metadata.at("lastModified");
                 }
             } catch (const nlohmann::json::exception & e) {
                 fprintf(stderr, "%s: error reading metadata file %s: %s\n", __func__, metadata_path.c_str(), e.what());

common/common.h

@@ -141,6 +141,7 @@ struct gpt_params {
     bool use_color         = false; // use color to distinguish generations and inputs
     bool interactive       = false; // interactive mode
     bool interactive_specials = false; // whether to allow special tokens from user, during interactive mode
+    bool conversation      = false; // conversation mode (does not print special tokens and suffix/prefix)
     bool chatml            = false; // chatml mode (used for models trained on chatml syntax)
     bool prompt_cache_all  = false; // save user input and generations to prompt cache
     bool prompt_cache_ro   = false; // open the prompt cache read-only and do not update it

common/json-schema-to-grammar.h

@@ -1,4 +1,8 @@
 #pragma once
+
+#include "ggml.h"
+// Change JSON_ASSERT from assert() to GGML_ASSERT:
+#define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
 
 std::string json_schema_to_grammar(const nlohmann::ordered_json& schema);

common/sampling.cpp

@@ -35,6 +35,8 @@ struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_
 
     result->prev.resize(params.n_prev);
 
+    result->n_considered = 0;
+
     llama_sampling_set_rng_seed(result, params.seed);
 
     return result;
@@ -64,6 +66,7 @@ void llama_sampling_reset(llama_sampling_context * ctx) {
 
     std::fill(ctx->prev.begin(), ctx->prev.end(), 0);
     ctx->cur.clear();
+    ctx->n_considered = 0;
 }
 
 void llama_sampling_set_rng_seed(struct llama_sampling_context * ctx, uint32_t seed) {
@@ -253,6 +256,8 @@ static llama_token llama_sampling_sample_impl(
         }
     }
 
+    ctx_sampling->n_considered = cur_p.size;
+
     return id;
 }
 

common/sampling.h

@@ -81,6 +81,7 @@ struct llama_sampling_context {
     // TODO: replace with ring-buffer
     std::vector<llama_token>      prev;
     std::vector<llama_token_data> cur;
+    size_t n_considered;
 
     std::mt19937 rng;
 };

convert-hf-to-gguf-update.py

@@ -49,6 +49,10 @@ class TOKENIZER_TYPE(IntEnum):
 
 if len(sys.argv) == 2:
     token = sys.argv[1]
+    if not token.startswith("hf_"):
+        logger.info("Huggingface token seems invalid")
+        logger.info("Usage: python convert-hf-to-gguf-update.py <huggingface_token>")
+        sys.exit(1)
 else:
     logger.info("Usage: python convert-hf-to-gguf-update.py <huggingface_token>")
     sys.exit(1)
@@ -67,6 +71,9 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "gpt-2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
     {"name": "refact",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
     {"name": "command-r",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
+    {"name": "qwen2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
+    {"name": "olmo",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
+    {"name": "dbrx",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
 ]
 
 # make directory "models/tokenizers" if it doesn't exist
@@ -150,6 +157,8 @@ def download_file_with_auth(url, token, save_path):
     # print the "pre_tokenizer" content from the tokenizer.json
     with open(f"models/tokenizers/{name}/tokenizer.json", "r", encoding="utf-8") as f:
         cfg = json.load(f)
+        normalizer = cfg["normalizer"]
+        logger.info("normalizer: " + json.dumps(normalizer, indent=4))
         pre_tokenizer = cfg["pre_tokenizer"]
         logger.info("pre_tokenizer: " + json.dumps(pre_tokenizer, indent=4))
 
@@ -252,6 +261,7 @@ def get_vocab_base_pre(self, tokenizer) -> str:
     "3333333",
     "33333333",
     "333333333",
+    # "Cửa Việt", # llama-bpe fails on this
     chktxt,
 ]