Xuan Son Nguyen
4bf7ca3943
llama_decode_ext
2025-02-24 17:01:20 +01:00
Xuan Son Nguyen
17d3658b5f
move to llama_batch_ext
2025-02-16 00:02:53 +01:00
Xuan Son Nguyen
f2e59a8eb9
rework, targeting llama-server
2025-02-14 18:16:49 +01:00
Xuan Son Nguyen
4ed4fe75ed
first proposal for private llama_batch
2025-02-14 00:48:12 +01:00
Olivier Chafik
c7f460ab88
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none (#11607 )
...
* extract & return thoughts in reasoning_content field (unless --reasoning-format) for DeepSeek R1 & Command R7B
* tool-calls: add deepseek r1 template (models/templates/llama-cpp-deepseek-r1.jinja) + hackommodate broken official template
* tool-calls: accommodate variety of wrong tool call opening tags both R1 Qwen 32B and 7B distills like to spit out
* server/oai: ensure content is null when there are tool calls, and reasoning_content appears before content for readability
* tool-calls: add DeepSeek R1 Qwen distills to server/README.md & server tests
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-02-13 10:05:16 +00:00
Vinesh Janarthanan
27e8a23300
sampling: add Top-nσ sampler ( #11223 )
...
* initial sampling changes:
* completed top nsigma sampler implementation
* apply parameter to only llama-cli
* updated readme
* added tests and fixed nsigma impl
* cleaned up pr
* format
* format
* format
* removed commented tests
* cleanup pr and remove explicit floats
* added top-k sampler to improve performance
* changed sigma to float
* fixed string format to float
* Update src/llama-sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update common/sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update src/llama-sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update src/llama-sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update src/llama-sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update src/llama-sampling.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* added llama_sampler_init
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-02-13 08:45:57 +02:00
Daniel Bevenius
3e69319772
llama : update llama_decode_internal ref [no ci] ( #11840 )
...
This commit updates the comment in llama_kv_cache.h to reflect the
change of the function name from llama_decode_internal to
llama_decode_impl.
2025-02-13 08:07:51 +02:00
bandoti
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf ( #11811 )
2025-02-12 10:06:53 -04:00
Daniel Bevenius
369be5598a
llama : fix typo in llama-grammar.h [no ci] ( #11816 )
2025-02-12 09:40:01 +02:00
Wilken Gottwalt
19b392d58d
llama-mmap: fix missing include ( #11796 )
...
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;
| ^~~~~~~~
2025-02-10 20:58:18 +02:00
Georgi Gerganov
bdcf8b6a56
cont : fix mmap flag print ( #11699 )
2025-02-08 16:49:38 +02:00
Georgi Gerganov
ed926d8833
llama : fix defrag logic ( #11707 )
...
* llama : fix defrag logic
ggml-ci
* cont : better logic
ggml-ci
* cont : clamp fragmentation to 0.0
ggml-ci
2025-02-07 16:05:34 +02:00
Christian Fillion
2d219b389e
vocab : ignore invalid UTF-8 input in the BPE tokenizer ( #11729 )
...
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.
2025-02-07 15:55:47 +02:00
magicse
333820d749
llama : fix progress dots ( #11730 )
...
* 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
2025-02-07 15:48:47 +02:00
Christian Fillion
7ee953a64a
llama : add llama_sampler_init for safe usage of llama_sampler_free ( #11727 )
...
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.
2025-02-07 11:33:27 +02:00
tv1wnd
855cd0734a
llama : fix old glm4 models ( #11670 )
2025-02-06 22:48:51 +01:00
Georgi Gerganov
9dd7a0390f
llama : add log about loading model tensors ( #11699 )
2025-02-06 13:41:37 +02:00
Johannes Gäßler
fd08255d0d
CUDA: non-contiguous (RMS) norm support ( #11659 )
...
* CUDA: non-contiguous (RMS) norm support
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-02-04 22:21:42 +01:00
Olivier Chafik
90f9b88afb
nit: more informative crash when grammar sampler fails ( #11593 )
2025-02-02 19:58:34 +00:00
piDack
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models ( #10573 )
...
* 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 >
2025-02-02 09:48:46 +02:00
Olivier Chafik
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars ( #9639 )
...
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2025-01-30 19:13:58 +00:00
mgroeber9110
ffd0821c57
vocab : correctly identify LF token for GPT-2 style BPE tokenizer ( #11496 )
2025-01-30 12:10:59 +02:00
Molly Sophia
325afb370a
llama: fix missing k_cache store for rwkv6qwen2 ( #11445 )
...
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
2025-01-29 12:07:21 +08:00
lexasub
a5203b4465
llama : minor fixes for up llama load model speed ( #11448 )
...
* 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 >
2025-01-27 14:42:09 +01:00
Johannes Gäßler
df984e0147
llama: refactor llama_decode_impl ( #11381 )
2025-01-27 12:07:12 +01:00
Frank Mai
1d8ee06000
rpc: fix register position ( #11424 )
...
Signed-off-by: thxCode <thxcode0824@gmail.com >
2025-01-26 16:20:34 +01:00
Olivier Chafik
6171c9d258
Add Jinja template support ( #11016 )
...
* Copy minja from 58f0ca6dd7https://github.com/google/minja/pull/22 )
* Apply suggestions from code review
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Finish suggested renamings
* Move chat_templates inside server_context + remove mutex
* Update --chat-template-file w/ recent change to --chat-template
* Refactor chat template validation
* Guard against missing eos/bos tokens (null token otherwise throws in llama_vocab::impl::token_get_attr)
* Warn against missing eos / bos tokens when jinja template references them
* rename: common_chat_template[s]
* reinstate assert on chat_templates.template_default
* Update minja to b8437df626https://github.com/google/minja/pull/25
* Update minja from https://github.com/google/minja/pull/27
* rm unused optional header
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-01-21 13:18:51 +00:00
Christopher Nielsen
90d987b105
mmap: add include for cerrno ( #11296 )
...
ggml-ci
Co-authored-by: Xuan Son Nguyen <son@huggingface.co >
2025-01-20 16:02:43 +02:00
Xuan Son Nguyen
ec7f3ac9ab
llama : add support for Deepseek-R1-Qwen distill model ( #11310 )
...
* llama : add support for Deepseek-R1-Qwen distill model
* coding style
2025-01-20 14:35:07 +01:00
Georgi Gerganov
ef6dada60c
cont : fix whitespaces ( #11305 )
2025-01-20 09:29:32 +02:00
Kyle Bruene
ae3c1db2f9
llama : re-add LLM_ARCH_PHIMOE ( #11305 )
...
Phi 3.5 MoE was partially removed during a refactor. The code was originally in llama.cpp and should be in llama-model.cpp after the refactor.
2025-01-20 09:21:01 +02:00
Georgi Gerganov
4dd34ff831
cmake : add sanitizer flags for llama.cpp ( #11279 )
...
* cmake : add sanitizer flags for llama.cpp
ggml-ci
* tests : fix compile warnings
ggml-ci
* cmake : move sanitizer flags to llama_add_compile_flags
ggml-ci
* cmake : move llama.cpp compile flags to top level lists
ggml-ci
* cmake : apply only sanitizer flags at top level
ggml-ci
* tests : fix gguf context use in same_tensor_data
* gguf-test: tensor data comparison
* dummy : trigger ggml-ci
* unicode : silence gcc warnings
ggml-ci
* ci : use sanitizer builds only in Debug mode
ggml-ci
* cmake : add status messages [no ci]
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de >
2025-01-18 16:18:15 +02:00
Radoslav Gerganov
667d72846c
rpc : early register backend devices ( #11262 )
...
Early register RPC devices and do not propagate RPC specifics in the
llama model structures.
ref: #10609
2025-01-17 10:57:09 +02:00
Georgi Gerganov
a133566d34
vocab : fix double-eos check ( #11273 )
...
ggml-ci
2025-01-17 09:28:00 +02:00
Xuan Son Nguyen
681149ced2
llama : add llama_model_load_from_splits ( #11255 )
...
* llama : add `llama_model_load_from_splits`
* update
2025-01-16 13:54:08 +01:00
Johannes Gäßler
432df2d5f9
RoPE: fix back, CUDA support for back + noncont. ( #11240 )
...
* RoPE: fix back, CUDA support for back + noncont.
* fix comments reg. non-cont. RoPE support [no-ci]
2025-01-15 12:51:37 +01:00
Georgi Gerganov
bbf3e55e35
vocab : add dummy tokens for "no_vocab" type ( #11231 )
...
* vocab : add dummy tokens for "no_vocab" type
ggml-ci
* vocab : minor [no ci]
2025-01-14 11:54:58 +01:00
Daniel Bevenius
8f70fc3d1b
llama : remove 'd' from bad special token log ( #11212 )
...
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
```
2025-01-13 13:38:20 +01:00
Xuan Son Nguyen
9a483999a6
llama : fix chat template gguf key ( #11201 )
2025-01-12 13:45:14 +01:00
Georgi Gerganov
08f10f69c3
llama : remove notion of CLS token ( #11064 )
...
ggml-ci
2025-01-12 12:15:53 +02:00
Georgi Gerganov
afa8a9ec9b
llama : add llama_vocab, functions -> methods, naming ( #11110 )
...
* llama : functions -> methods (#11110 )
* llama : add struct llama_vocab to the API (#11156 )
ggml-ci
* hparams : move vocab params to llama_vocab (#11159 )
ggml-ci
* vocab : more pimpl (#11165 )
ggml-ci
* vocab : minor tokenization optimizations (#11160 )
ggml-ci
Co-authored-by: Diego Devesa <slarengh@gmail.com >
* lora : update API names (#11167 )
ggml-ci
* llama : update API names to use correct prefix (#11174 )
* llama : update API names to use correct prefix
ggml-ci
* cont
ggml-ci
* cont
ggml-ci
* minor [no ci]
* vocab : llama_vocab_add_[be]os -> llama_vocab_get_add_[be]os (#11174 )
ggml-ci
* vocab : llama_vocab_n_vocab -> llama_vocab_n_tokens (#11174 )
ggml-ci
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com >
2025-01-12 11:32:42 +02:00
Molly Sophia
ee7136c6d1
llama: add support for QRWKV6 model architecture ( #11001 )
...
llama: add support for QRWKV6 model architecture (#11001 )
* WIP: Add support for RWKV6Qwen2
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* RWKV: Some graph simplification
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Add support for RWKV6Qwen2 with cpu and cuda GLA
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* RWKV6[QWEN2]: Concat lerp weights together to reduce cpu overhead
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Fix some typos
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* code format changes
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Fix wkv test & add gla test
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Fix cuda warning
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Update README.md
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Update ggml/src/ggml-cuda/gla.cu
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Fix fused lerp weights loading with RWKV6
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* better sanity check skipping for QRWKV6 in llama-quant
thanks @compilade
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
Co-authored-by: compilade <git@compilade.net >
---------
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
Co-authored-by: compilade <git@compilade.net >
2025-01-10 09:58:08 +08:00
Pierrick Hymbert
f8feb4b01a
model: Add support for PhiMoE arch ( #11003 )
...
* model: support phimoe
* python linter
* doc: minor
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com >
* doc: minor
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com >
* doc: add phimoe as supported model
ggml-ci
---------
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com >
2025-01-09 11:21:41 +01:00
Xuan Son Nguyen
d9feae1c06
llama-chat : add phi 4 template ( #11148 )
2025-01-09 10:07:33 +01:00
Xuan Son Nguyen
4d2b3d8804
lora : improve compat with mergekit-extract-lora ( #11131 )
...
* (wip) support mergekit-extracted lora
* support mergekit-extract-lora
* use lora->get_scale
* correct comment
* correct norm name & condition
* add some hints
2025-01-08 15:59:53 +01:00
Georgi Gerganov
c07d437bbd
llama : avoid hardcoded QK_K ( #11061 )
...
ggml-ci
2025-01-08 16:19:36 +02:00
Johannes Gäßler
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes ( #11030 )
...
* 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
2025-01-07 18:01:58 +01:00
Georgi Gerganov
ecebbd292d
llama : remove unused headers ( #11109 )
...
ggml-ci
2025-01-06 17:52:35 +02:00
Xuan Son Nguyen
09186fabbe
llama : remove check flash_attn with lora ( #11104 )
2025-01-06 13:41:12 +01:00
Asghar Ghorbani
96a1dc27c3
llama : prevent system info string accumulation across calls ( #11101 )
2025-01-06 13:21:46 +02:00
