Technically the fixed width types come only from iostream and
cstdint/stdint.h headers. memory and vector headers should not provide
these. In GCC 15 the headers are cleaned up and you require the proper
header cstdint.
src/llama-mmap.h:26:5: error: ‘uint32_t’ does not name a type
26 | uint32_t read_u32() const;
| ^~~~~~~~
Silently insert U+FFFD(s) (Unicode replacement character) instead until the
next valid codepoint can be found.
This fixes `llama_tokenize` throwing an exception across the C API boundary
or libllama's module boundary (the caller's runtime might be incompatible!)
Returing a proper error code might be desirable, however the signature
of `llama_tokenize` doesn't allow it as all return values already have
existing meaning.
* Update llama.cpp
For display progress dots in terminal.
Without this it didn't display dots progress during loading model from file.
* Update llama.cpp
removed trailing spaces
The C API in llama.h claims users can implement `llama_sampler_i` to
create custom `llama_sampler`. The sampler chain takes ownership and
calls `llama_sampler_free` on them. However, `llama_sampler_free` is
hard-coded to use `delete`. This is undefined behavior if the object
wasn't also allocated via `new` from libllama's C++ runtime. Callers
in C and C-compatible languages do not use C++'s `new` operator. C++
callers may not be sharing the same heap as libllama.
* add glm edge chat model
* use config partial_rotary_factor as rope ratio
* support for glm edge model
* vision model support
* remove debug info
* fix format
* llava.cpp trailing whitespace
* remove unused AutoTokenizer
* Update src/llama.cpp for not contain <|end|> or </s>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* add edge template
* fix chat template
* fix confict
* fix confict
* fix ci err
* fix format err
* fix template err
* 9b hf chat support
* format
* format clip.cpp
* fix format
* Apply suggestions from code review
* Apply suggestions from code review
* Update examples/llava/clip.cpp
* fix format
* minor : style
---------
Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* impl::load change map bpe_ranks to onordered map for reduce time of impl::load on 30%
* llama_model_loader::init_mapping - replace new llama_mmap to std::make_unique<llama_mmap> for clean code & reduce (/2) time of running init_mappings
* Update src/llama-vocab.cpp
---------
Co-authored-by: lexasub <empty@empty.ru>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit removes the 'd' from the log message in llama-vocab.cpp
when logging a bad special token.
The motivation for this is that currently the output can look something
like the following:
```console
load: bad special token:
'tokenizer.ggml.image_token_id' = 128256d, using default id -1
```
* (wip) support mergekit-extracted lora
* support mergekit-extract-lora
* use lora->get_scale
* correct comment
* correct norm name & condition
* add some hints
* GGUF: C++ refactor, backend support, misc fixes
remove ggml_tensor.backend
update CODEOWNERS [no ci]
remove gguf_get_data from API
revise GGUF API data types
This commit renames the `batch` parameter to `ubatch` in the
`llama_kv_cache_find_slot`, `llm_build_inp_embd`, and
`llm_build_mamba` functions.
The motivation for this is that this should have been done as part of
Commit 19d900a756 ("llama : rename batch
to ubatch (#9950)") but for some reason I missed these functions in
that commit and only noticed them now (sorry).
* convert : extend DEEPSEEK2 model architecture to support DeepseekV3ForCausalLM by adding EXPERT_WEIGHTS_NORM and EXPERT_GATING_FUNC model parameters and FFN_EXP_PROBS_B tensor type
* vocab : add DeepSeek V3 pre-tokenizer regexes
* unicode : handle ACCENT_MARK and SYMBOL categories in regex
* llama : add DeepSeek V3 chat template, handle new model parameters and tensor types
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
