Daniel Bevenius [Mon, 12 Feb 2024 08:38:44 +0000 (09:38 +0100)]
llava : remove prog parameter from ArgumentParser (#5457)
* llava: remove prog parameter from ArgumentParser
This commit removes the `prog` parameter from `ArgumentParser`
so that it uses the default value which is the name of the script.
The motivation for this change is that currently the usage output looks
like this:
```console
$ python examples/llava/convert-image-encoder-to-gguf.py --help
usage: convert_hf_to_gguf.py [-h] ...
```
And with this change it will look like this:
```console
$ python examples/llava/convert-image-encoder-to-gguf.py --help
usage: convert-image-encoder-to-gguf.py [-h] ...
```
Signed-off-by: Daniel Bevenius <redacted>
* ci: add W503 to flake8 ignore list
This commit adds W503 to the ignore list for flake8. This is done to
avoid the following error:
W503 line break before binary operator
Signed-off-by: Daniel Bevenius <redacted>
---------
Douglas Hanley [Sun, 11 Feb 2024 16:21:38 +0000 (10:21 -0600)]
Add support for BERT embedding models (#5423)
* BERT model graph construction (build_bert)
* WordPiece tokenizer (llm_tokenize_wpm)
* Add flag for non-causal attention models
* Allow for models that only output embeddings
* Support conversion of BERT models to GGUF
* Based on prior work by @xyzhang626 and @skeskinen
---------
Co-authored-by: Jared Van Bortel <redacted> Co-authored-by: Jared Van Bortel <redacted> Co-authored-by: Georgi Gerganov <redacted>
snadampal [Sun, 11 Feb 2024 13:22:33 +0000 (07:22 -0600)]
ggml : add mmla kernels for quantized GEMM (#4966)
* ggml: aarch64: implement smmla kernel for q8_0_q8_0 quantized gemm
armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q8_0_q8_0 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"
On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.
* ggml: aarch64: implement smmla kernel for q4_0_q8_0 quantized gemm
armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q4_0_q8_0 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"
On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.
* ggml: aarch64: implement smmla kernel for q4_1_q8_1 quantized gemm
armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q4_1_q8_1 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"
On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.
* ggml: update unit tests for the new vec_dot interface
* llama.cpp: add MATMUL_INT8 capability to system_info
Neuman Vong [Fri, 9 Feb 2024 18:30:19 +0000 (05:30 +1100)]
vulkan: Set limit for task concurrency (#5427)
A common default for the maximum number of open files is 256, which can
lead to `asyncio.gather(*tasks)` failing with Too many open files.
$ python ggml_vk_generate_shaders.py --glslc=$ANDROID_NDK_PATH/shader-tools/darwin-x86_64/glslc
ggml_vulkan: Generating and compiling shaders to SPIR-V
Traceback (most recent call last):
File "/Users/neuman/Code.noindex/github/llama.cpp/ggml_vk_generate_shaders.py", line 2326, in <module>
asyncio.run(main())
File "/Users/neuman/Code.noindex/miniforge3/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/Users/neuman/Code.noindex/miniforge3/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/Users/neuman/Code.noindex/github/llama.cpp/ggml_vk_generate_shaders.py", line 2294, in main
await asyncio.gather(*tasks)
[...snip...]
OSError: [Errno 24] Too many open files
This change sets a reasonable concurrency limit for tasks (and therefore
open files), without significant impact on run time.
Daniel Bevenius [Fri, 9 Feb 2024 13:00:59 +0000 (14:00 +0100)]
llava : add requirements.txt and update README.md (#5428)
* llava: add requirements.txt and update README.md
This commit adds a `requirements.txt` file to the `examples/llava`
directory. This file contains the required Python packages to run the
scripts in the `examples/llava` directory.
The motivation of this to make it easier for users to run the scripts in
`examples/llava`. This will avoid users from having to possibly run into
missing package issues if the packages are not installed on their system.
Signed-off-by: Daniel Bevenius <redacted>
* llava: fix typo in llava-surgery.py output
Signed-off-by: Daniel Bevenius <redacted>
---------
Daniel Bevenius [Thu, 8 Feb 2024 14:20:03 +0000 (15:20 +0100)]
llava : add missing .py, and fix paths in README.md (#5414)
This commit adds the missing .py extension to the convert-image-encoder-to-gguf
script. It also fixes the paths for the `model` and `mmproj` options in the
example llava-cli command.
Dr. Tom Murphy VII Ph.D [Mon, 5 Feb 2024 11:13:57 +0000 (06:13 -0500)]
ggml : avoid duplicating function calls using MIN/MAX macros (#5325)
* Avoid duplicating function calls when using MIN/MAX macros.
Since these copy "a" and "b" they ask the compiler to evaluate one of them twice. The compiler doesn't have a problem with removing the duplication in something like MAX(0, x + 2), but in some cases we're calling functions, and those calls just happen twice.
By explicitly evaluating at the expression we get smaller and faster code without duplicate calls. See ggml_rope_yarn_corr_dims in Compiler Explorer:
Kawrakow [Mon, 5 Feb 2024 08:46:06 +0000 (10:46 +0200)]
iq2_xxs: tune quantization (#5320)
We get slightly better PPL, and we cut quantization time in
nearly half.
The trick is to 1st quantize without forcing points onto the E8-lattice.
We can then use a narrower search range around the block scale that we
got that way.
Ian Bull [Fri, 2 Feb 2024 07:20:13 +0000 (23:20 -0800)]
llama : fix memory leak in llama_batch_free (#5252)
The llama_batch_init allocates memory for a fixed number of tokens.
However, the llama_batch_free only frees memory for the number of
tokens that were added to the batch.
This change-set uses a null terminated array for the batch seq_id, and
frees all the elements until the nullptr is reached. This change-set
also changes the name of the first parameter from `n_tokens` to
`n_tokens_alloc` to more clearly indicate that this value is the number
of tokens allocated to the batch, not the number of tokens in the batch.
overview / pkg / ggml / sources / llama.cpp / log