Georgi Gerganov
6f54ee660c
retrieval : avoid common_batch
...
ggml-ci
2025-03-19 13:50:15 +02:00
Xuan Son Nguyen
dc4bb64290
Merge branch 'master' into xsn/private_batch_api
2025-03-18 15:45:22 +01:00
Xuan Son Nguyen
624a683c6f
fix compile
2025-03-14 22:30:29 +01:00
Xuan Son Nguyen
116b9a1662
rename to init_from_text
2025-03-14 22:17:07 +01:00
Xuan Son Nguyen
eaffba0f2e
llama_batch_ext_ptr::from_text/embd
2025-03-14 17:12:03 +01:00
fairydreaming
8fcb563613
Load all MoE experts during warmup ( #11571 )
...
* llama : introduce llama_set_warmup() API call that controls warmup mode; use all MoE experts during warmup
* common : use new API to enable warmup mode during model warmup
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com >
2025-03-14 13:47:05 +01:00
Xuan Son Nguyen
a363251fac
qwen2vl: use llama_batch_ext_set_pos
2025-03-14 11:25:36 +01:00
Xuan Son Nguyen
ba79369615
fix llama_batch_ext_init_from_embd
2025-03-14 11:17:22 +01:00
Xuan Son Nguyen
54566ad95d
correct comment
2025-03-14 00:21:06 +01:00
Xuan Son Nguyen
c3dd79007b
fix llama_batch_ext_init_from_text
2025-03-13 23:09:27 +01:00
Xuan Son Nguyen
47086fa82d
apply to the rest
2025-03-13 22:36:27 +01:00
Xuan Son Nguyen
4aabf4e8f4
return output ID from llama_batch_ext_add/set
2025-03-13 17:47:07 +01:00
Xuan Son Nguyen
86973cb14a
fix merge errors
2025-03-13 17:32:36 +01:00
Xuan Son Nguyen
17f954c8e2
Merge branch 'master' into xsn/private_batch_api
2025-03-13 15:55:18 +01:00
Georgi Gerganov
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context ( #12181 )
...
* llama : refactor llama_context, llama_kv_cache, llm_build_context
ggml-ci
* graph : don't mutate the KV cache during defrag
ggml-ci
* context : reduce virtuals + remove test function
ggml-ci
* context : move interface implementation to source file + factory
ggml-ci
* graph : move KV cache build functions to llama_context impl
ggml-ci
* graph : remove model reference from build_pooling
ggml-ci
* graph : remove llama_model reference
ggml-ci
* kv_cache : provide rope factors
ggml-ci
* graph : rework inputs to use only unique_ptr, remove attn input abstraction
ggml-ci
* context : remove llama_context_i abstraction
ggml-ci
* context : clean-up
ggml-ci
* graph : clean-up
ggml-ci
* llama : remove redundant keywords (struct, enum)
ggml-ci
* model : adapt gemma3
ggml-ci
* graph : restore same attention ops as on master
ggml-ci
* llama : remove TODO + fix indent
ggml-ci
2025-03-13 12:35:44 +02:00
Olivier Chafik
669912d9a5
tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034 )
...
* sampler: turn lazy grammar trigger words to regexes
* add scripts/tool_bench.sh & .py
* constrain llama json output regardless of function name if matches at beginning
* update relaxed newline space rule in grammar tests
* support add_generation_prompt query parameter (useful for /apply_template)
* Update src/llama-grammar.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-03-05 13:05:13 +00:00
Xuan Son Nguyen
1d6ba97789
remove token_info API
2025-03-01 16:21:16 +01:00
Xuan Son Nguyen
1170135dfb
llama_batch_ext_add_text
2025-03-01 14:00:14 +01:00
Xuan Son Nguyen
9e75c49d35
Merge branch 'master' into xsn/private_batch_api
2025-03-01 12:13:03 +01:00
Xuan-Son Nguyen
c43a3e7996
llama : add Phi-4-mini support (supersede #12099 ) ( #12108 )
...
* Added Phi-4-mini-instruct support
* Update regex per ngxson
* Change the vocab base to Xenova/gpt-4o
* fix conversion update script
* no need to check longrope
* minor style fix
* fix python style
---------
Co-authored-by: Nicholas Sparks <nisparks@microsoft.com >
2025-02-28 12:44:11 +01:00
Vitali Lovich
3e9a2860e9
llama : expose llama_model_n_head_kv in the API ( #11997 )
...
It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).
2025-02-25 11:29:33 +02:00
Xuan Son Nguyen
a1b1dea33b
Merge branch 'master' into xsn/private_batch_api
2025-02-24 17:01:30 +01:00
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
Georgi Gerganov
68ff663a04
repo : update links to new url ( #11886 )
...
* repo : update links to new url
ggml-ci
* cont : more urls
ggml-ci
2025-02-15 16:40:57 +02:00
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
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
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
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
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
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
David Renshaw
960ec65273
llama : fix deprecation message: vocabable -> vocab ( #11269 )
2025-01-17 08:12:01 +01:00
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
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
Georgi Gerganov
47182dd03f
llama : update llama_model API names ( #11063 )
...
* llama : deprecate llama_free_model, add llama_model_free
ggml-ci
* llama : change `llama_load_model_from_file` -> `llama_model_load_from_file`
ggml-ci
2025-01-06 10:55:18 +02:00
Georgi Gerganov
727368c60f
llama : use LLAMA_TOKEN_NULL ( #11062 )
...
ggml-ci
2025-01-06 10:52:15 +02:00
fairydreaming
9394bbd484
llama : Add support for DeepSeek V3 ( #11049 )
...
* 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 >
2025-01-04 21:06:11 +01:00
Georgi Gerganov
f66f582927
llama : refactor src/llama.cpp ( #10902 )
...
* llama : scatter llama.cpp into multiple modules (wip)
* llama : control-vector -> adapter
* llama : arch
* llama : mmap
ggml-ci
* ci : remove BUILD_SHARED_LIBS=OFF
ggml-ci
* llama : arch (cont)
ggml-ci
* llama : chat
ggml-ci
* llama : model
ggml-ci
* llama : hparams
ggml-ci
* llama : adapter
ggml-ci
* examples : fix
ggml-ci
* rebase
ggml-ci
* minor
* llama : kv cache
ggml-ci
* llama : impl
ggml-ci
* llama : batch
ggml-ci
* cont
ggml-ci
* llama : context
ggml-ci
* minor
* llama : context (cont)
ggml-ci
* llama : model loader
ggml-ci
* common : update lora
ggml-ci
* llama : quant
ggml-ci
* llama : quant (cont)
ggml-ci
* minor [no ci]
2025-01-03 10:18:53 +02:00
Georgi Gerganov
0bf2d10c55
tts : add OuteTTS support ( #10784 )
...
* server : add "tokens" output
ggml-ci
* server : output embeddings for all tokens when pooling = none
ggml-ci
* server : be explicit about the pooling type in the tests
ggml-ci
* server : do not normalize embeddings when there is no pooling
ggml-ci
* llama : add OuteTTS support (wip)
* wip
* extract features
* first conv
* group norm
* resnet conv
* resnet
* attn
* pos net
* layer norm
* convnext
* head
* hann window
* fix n_embd + remove llama.cpp hacks
* compute hann window
* fft
* spectrum processing
* clean-up
* tts : receive input text and generate codes
* clip : fix new conv name
* tts : minor fix
* tts : add header + minor fixes
ggml-ci
* tts : add matchematical constant
ggml-ci
* tts : fix sampling + cut initial noise
* tts : fixes
* tts : update default samplers
ggml-ci
* tts : text pre-processing
* tts : outetts-voc -> wavtokenizer-dec
* tts : remove hardcoded constants
ggml-ci
* tts : fix tensor shapes
* llama : refactor wavtokenizer tensors
ggml-ci
* cont
ggml-ci
* cont [no ci]
* llama : update WavTokenizer to non-causal attn
* llama : handle no-vocab detokenization
* tts : add Python example for OuteTTS (wip)
* tts : extend python example to generate spectrogram
ggml-ci
* server : fix rebase artifacts
* tts : enable "return_tokens" in Python example
ggml-ci
* tts : minor fixes
* common : support HF download for vocoder
2024-12-18 19:27:21 +02:00
Georgi Gerganov
644fd71b44
sampling : refactor + optimize penalties sampler ( #10803 )
...
* sampling : refactor + optimize penalties sampler
ggml-ci
* common : apply ignore_eos as logit bias
ggml-ci
* batched : remove penalties sampler
* params : allow penalty_last_n == -1 to be equal to context size
ggml-ci
* common : by default, move the penalties at the end of the sampling chain
ggml-ci
* common : ignore all EOG tokens
Co-authored-by: Diego Devesa <slarengh@gmail.com >
* common : move back the penalties at the front of the sampling chain
ggml-ci
* readme : restore hint about --ignore-eos flag [no ci]
* llama : minor
ggml-ci
* webui : update
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com >
2024-12-16 12:31:14 +02:00
HimariO
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE ( #10361 )
...
* Barebone Qwen2VL LLM convertor
* Add Qwen2VL cli entrypoint
* [WIP] add qwen2vl arch
* Verify m-rope output
* Add vl-rope/2d-rope support for qwen2vl ViT
* update qwen2vl cli tool
* update 5D tensor op workaround
* [WIP] qwen2vl vision model
* make batch and clip utils compatible with qwen2vl
* [WIP] create inference workflow, gguf convert script but fix
* correcting vision-rope behavior, add the missing last layer back to ViT
* add arg parser to qwen2vl_surgery
* replace variable size array with vector
* cuda-gdb cmake preset
* add fp32 mrope, vision rope kernel
* add fp16 support for qwen2vl and m-rope
* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`
* fix rope op mode switching, out dated func args
* update `llama_hparams`
* update to keep up stream changes
* resolve linter, test errors
* add makefile entry, update speical image padding token
* add mrope unit test, fix few compiler warnings
* rename `mrope` related function, params
* minor updates on debug util, bug fixs
* add `m-rope` testcase to `test-backend-ops`
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* fix traililng whitespce
* store `llama_hparams.rope_sections` with fixed size array
* update position id tensor size check in GGML_OP_ROPE
* minor updates
* update `ggml_backend_*_supports_op` of unsupported backends
* remote old `rope_section` compare operator
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-12-14 14:43:46 +02:00
kallewoof
484d2f31ae
bug-fix: snprintf prints NULL in place of the last character ( #10419 )
...
* bug-fix: snprintf prints NULL in place of the last character
We need to give snprintf enough space to print the last character and the null character, thus we allocate one extra byte and then ignore it when converting to std::string.
* add comment about extra null-term byte requirement
2024-12-11 14:48:04 +01:00
Djip007
19d8762ab6
ggml : refactor online repacking ( #10446 )
...
* rename ggml-cpu-aarch64.c to .cpp
* reformat extra cpu backend.
- clean Q4_0_N_M and IQ4_0_N_M
- remove from "file" tensor type
- allow only with dynamic repack
- extract cpu extra bufts and convert to C++
- hbm
- "aarch64"
- more generic use of extra buffer
- generalise extra_supports_op
- new API for "cpu-accel":
- amx
- aarch64
* clang-format
* Clean Q4_0_N_M ref
Enable restrict on C++
* add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack
* added/corrected control on tensor size for Q4 repacking.
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* add debug logs on repacks.
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-12-07 14:37:50 +02:00
Riccardo Orlando
6fe6247831
llama : add Minerva 7B model support ( #10673 )
...
* Support for Minerva 7B
* Update convert_hf_to_gguf_update.py
2024-12-05 20:30:59 +02:00
JFLFY2255
8d0cfd554a
llama: Support MiniCPM-1B (with & w/o longrope) ( #10559 )
2024-12-04 11:42:50 +02:00
Xuan Son Nguyen
3b4f2e33e2
llama : add missing LLAMA_API for llama_chat_builtin_templates ( #10636 )
2024-12-03 12:54:30 +01:00
Xuan Son Nguyen
642330ac7c
llama : add enum for built-in chat templates ( #10623 )
...
* llama : add enum for supported chat templates
* use "built-in" instead of "supported"
* arg: print list of built-in templates
* fix test
* update server README
2024-12-02 22:10:19 +01:00
Eric Curtin
0cc63754b8
Introduce llama-run ( #10291 )
...
It's like simple-chat but it uses smart pointers to avoid manual
memory cleanups. Less memory leaks in the code now. Avoid printing
multiple dots. Split code into smaller functions. Uses no exception
handling.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2024-11-25 22:56:24 +01:00
