2023-03-10 20:47:46 +01:00
# llama.cpp
2023-04-05 17:56:20 +02:00
2023-03-26 09:20:49 +02:00
2024-05-30 17:07:39 +02:00
[](https://opensource.org/licenses/MIT)
2024-07-19 13:34:55 +02:00
[](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml)
2023-03-12 21:09:26 +01:00
2023-10-04 15:50:44 +02:00
[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 )
2023-06-25 15:08:12 +02:00
2024-02-05 15:55:10 +01:00
Inference of Meta's [LLaMA ](https://arxiv.org/abs/2302.13971 ) model (and others) in pure C/C++
2023-03-10 20:47:46 +01:00
2024-07-05 18:08:32 +02:00
## Recent API changes
2024-03-03 11:44:03 +01:00
2024-09-03 09:00:36 +02:00
- [Changelog for `libllama` API ](https://github.com/ggerganov/llama.cpp/issues/9289 )
- [Changelog for `llama-server` REST API ](https://github.com/ggerganov/llama.cpp/issues/9291 )
2024-03-03 11:44:03 +01:00
2024-07-05 18:08:32 +02:00
## Hot topics
2023-08-27 13:44:35 +02:00
2024-11-01 16:31:51 +01:00
- **Introducing GGUF-my-LoRA** https://github.com/ggerganov/llama.cpp/discussions/10123
- Hugging Face Inference Endpoints now support GGUF out of the box! https://github.com/ggerganov/llama.cpp/discussions/9669
2024-09-27 19:57:51 +02:00
- Hugging Face GGUF editor: [discussion ](https://github.com/ggerganov/llama.cpp/discussions/9268 ) | [tool ](https://huggingface.co/spaces/CISCai/gguf-editor )
2023-08-18 16:48:31 +02:00
----
2023-03-14 08:43:52 +01:00
2023-03-10 20:47:46 +01:00
## Description
2024-02-05 15:55:10 +01:00
The main goal of `llama.cpp` is to enable LLM inference with minimal setup and state-of-the-art performance on a wide
2024-11-30 08:47:07 +01:00
range of hardware - locally and in the cloud.
2023-03-10 20:47:46 +01:00
2024-02-05 15:55:10 +01:00
- Plain C/C++ implementation without any dependencies
- Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
2024-10-18 07:34:36 +02:00
- AVX, AVX2, AVX512 and AMX support for x86 architectures
2024-02-19 08:39:31 +01:00
- 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
2024-10-12 07:09:53 +02:00
- Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads MTT GPUs via MUSA)
2024-06-04 20:23:20 +02:00
- Vulkan and SYCL backend support
2024-02-05 15:55:10 +01:00
- CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity
2023-03-10 20:47:46 +01:00
2024-11-30 08:47:07 +01:00
The `llama.cpp` project is the main playground for developing new features for the [ggml ](https://github.com/ggerganov/ggml ) library.
2023-03-11 11:31:21 +01:00
2024-11-30 08:47:07 +01:00
< details >
< summary > Models< / summary >
2023-03-29 18:37:20 +02:00
2024-02-07 07:21:30 +01:00
Typically finetunes of the base models below are supported as well.
2024-11-30 08:47:07 +01:00
Instructions for adding support for new models: [HOWTO-add-model.md ](./docs/development/HOWTO-add-model.md )
**Text-only:**
2023-03-30 21:31:54 +02:00
- [X] LLaMA 🦙
2023-07-28 03:14:11 +02:00
- [x] LLaMA 2 🦙🦙
2024-04-25 15:52:28 +02:00
- [x] LLaMA 3 🦙🦙🦙
2024-02-07 07:21:30 +01:00
- [X] [Mistral 7B ](https://huggingface.co/mistralai/Mistral-7B-v0.1 )
2024-02-05 15:55:10 +01:00
- [x] [Mixtral MoE ](https://huggingface.co/models?search=mistral-ai/Mixtral )
2024-04-13 11:33:52 +02:00
- [x] [DBRX ](https://huggingface.co/databricks/dbrx-instruct )
2024-04-21 14:35:40 +02:00
- [X] [Falcon ](https://huggingface.co/models?search=tiiuae/falcon )
2023-08-02 08:18:31 +02:00
- [X] [Chinese LLaMA / Alpaca ](https://github.com/ymcui/Chinese-LLaMA-Alpaca ) and [Chinese LLaMA-2 / Alpaca-2 ](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2 )
2023-03-30 21:31:54 +02:00
- [X] [Vigogne (French) ](https://github.com/bofenghuang/vigogne )
2024-07-01 13:40:58 +02:00
- [X] [BERT ](https://github.com/ggerganov/llama.cpp/pull/5423 )
2023-04-10 22:41:53 +02:00
- [X] [Koala ](https://bair.berkeley.edu/blog/2023/04/03/koala/ )
2023-10-17 20:13:21 +02:00
- [X] [Baichuan 1 & 2 ](https://huggingface.co/models?search=baichuan-inc/Baichuan ) + [derivations ](https://huggingface.co/hiyouga/baichuan-7b-sft )
- [X] [Aquila 1 & 2 ](https://huggingface.co/models?search=BAAI/Aquila )
2023-09-29 14:50:35 +02:00
- [X] [Starcoder models ](https://github.com/ggerganov/llama.cpp/pull/3187 )
2023-10-06 21:13:36 +02:00
- [X] [Refact ](https://huggingface.co/smallcloudai/Refact-1_6B-fim )
2023-10-11 01:02:49 +02:00
- [X] [MPT ](https://github.com/ggerganov/llama.cpp/pull/3417 )
2023-10-17 20:13:21 +02:00
- [X] [Bloom ](https://github.com/ggerganov/llama.cpp/pull/3553 )
2023-12-14 08:38:49 +01:00
- [x] [Yi models ](https://huggingface.co/models?search=01-ai/Yi )
2024-02-06 15:06:48 +01:00
- [X] [StableLM models ](https://huggingface.co/stabilityai )
2023-12-14 08:38:49 +01:00
- [x] [Deepseek models ](https://huggingface.co/models?search=deepseek-ai/deepseek )
- [x] [Qwen models ](https://huggingface.co/models?search=Qwen/Qwen )
2023-12-24 14:35:49 +01:00
- [x] [PLaMo-13B ](https://github.com/ggerganov/llama.cpp/pull/3557 )
2024-02-06 15:06:48 +01:00
- [x] [Phi models ](https://huggingface.co/models?search=microsoft/phi )
2023-12-28 15:03:57 +01:00
- [x] [GPT-2 ](https://huggingface.co/gpt2 )
2024-02-06 15:06:48 +01:00
- [x] [Orion 14B ](https://github.com/ggerganov/llama.cpp/pull/5118 )
- [x] [InternLM2 ](https://huggingface.co/models?search=internlm2 )
2024-02-05 08:41:38 +01:00
- [x] [CodeShell ](https://github.com/WisdomShell/codeshell )
2024-02-21 14:08:22 +01:00
- [x] [Gemma ](https://ai.google.dev/gemma )
llama : support Mamba Selective State Space Models (#5328)
* mamba : begin working on support for Mamba SSM
* mamba : begin figuring out how to (ab)use the kv cache for Mamba
* mamba : recurrent inference almost works, but incoherent
* mamba : recurrent inference WORKS!!!
* convert : optionally use d_conv and d_state from config.json for Mamba
* mamba : refactor recurrent conv, resulting in 20% perf increase
It's still slower than I'd like, but I did not really optimize `ggml_exp` yet.
I also refactored `ggml_exp` to work with tensors with more than 2 dimensions.
* ggml : parallelize ggml_exp
This results in 8% faster token generation for Mamba-130M.
* mamba : simplify the conv step with a self-overlapping view
Turns out the conv_state can be made smaller by one column.
Note that this breaks existing GGUFs of Mamba,
because the key_value_length field is tied to the conv_state size.
Convolution with a self-overlapping view is cool!
And it's much simpler than what I initially thought would be necessary
to make the convolution step work with more than 1 token at a time.
Next step is to make the SSM step work on batches of tokens too,
and thus I need to figure out a way to make a parallel selective scan
which will keep the ssm_state small and won't make it bigger
by a factor of (n_layer * batch_size).
* llama : fix Mamba KV self size wrongly displaying as f16 instead of f32
Relatedly, I also tried to see if other types than f32 worked for the states,
but they don't, because of the operators used.
It's probably better anyway to keep lots of precision there,
since the states are small anyway.
* mamba : fix self-overlapping view depth stride
* mamba : handle batches of more than 1 token
This means running Mamba no longer crashes when using the default settings!
And probably also slightly faster prompt processing.
Both batched and non-batched processing yield the same output.
Previously, the state was not cleared when starting a sequence.
Next step is to make the KV cache API work as expected for Mamba models.
* ggml: add ggml_ssm_scan to help with parallel selective scan
If the selective scan was implemented without a custom operator,
there would be waaay too many nodes in the graph. For example,
for Mamba-130M, with a batch size of 512 (the default),
a naive selective scan could add at least 24*512=12288 nodes,
which is more than LLAMA_MAX_NODES (8192),
and that's only for the smallest Mamba model.
So it's much cleaner with a custom operator.
Not sure about the name, though.
* ggml : in ggml_ssm_scan, merge multiple rows in the same vec operation
This will help with performance on CPU if ggml_vec_mul_f32
and ggml_vec_add_f32 are ever optimized with SIMD.
* mamba : very basic quantization support
Mostly works, but there is currently no difference
between the variants of a k-quant (e.g. Q4_K_S and Q4_K_M are the same).
Most of the SSM-specific weights can be kept in f32 without affecting
the size that much, since they are relatively small.
(the linear projection weights are responsible for most of Mamba's size)
Too much quantization seems to make the state degrade quite fast, and
the model begins to output gibberish.
It seems to affect bigger models to a lesser extent than small models,
but I'm not sure by how much.
Experimentation will be needed to figure out which weights are more important
for the _M (and _L?) variants of k-quants for Mamba.
* convert : fix wrong name for layer norm weight of offical Mamba models
I was using Q-bert/Mamba-* models before, which have a slighlty different
naming scheme for the weights.
(they start with "model.layers" instead of "backbone.layers")
* mamba : fuse more steps of the SSM scan in the ggml_ssm_scan operator
This increases performance on CPU by around 30% for prompt processing,
and by around 20% for text generation.
However, it also makes the ggml_exp and ggml_soft_plus operators unused.
Whether or not they should be kept will be decided later.
* convert : for Mamba, also consider the "MambaLMHeadModel" arch name
It's the name of the class of the official implementation,
though they don't use it (yet) in the "architectures" field of config.json
* mamba : fix vocab size problems with official models
The perplexity was waaaay to high for models with a non-round vocab size.
Not sure why, but it needed to be fixed in the metadata.
Note that this breaks existing GGUF-converted Mamba models,
but **only if** the vocab size was not already rounded.
* ggml : remove ggml_exp and ggml_soft_plus
They did not exist anyway outside of this branch,
and since ggml_ssm_scan fused operations together, they are unused.
It's always possible to bring them back if needed.
* mamba : remove some useless comments
No code change.
* convert : fix flake8 linter errors
* mamba : apply suggestions from code review
* mamba : remove unecessary branch for row-wise ssm_state and C multiplication
It was previously done to avoid permuting when only one token is processed
at a time (like when generating text), but permuting is cheap,
and dynamically changing the compute graph is not future-proof.
* ggml : in ggml_ssm_scan, use more appropriate asserts
* ggml : rename the destination pointer in ggml_compute_forward_ssm_scan_f32
* mamba : multiple sequences, but one at a time
This is a step towards making this Mamba implementation usable
with the server example (the way the system prompt is kept when clearing
the client slots will need to be changed before this can work, though).
The KV cache size for this kind of model is tied to the maximum number
of sequences kept at any single time.
For now, this number is obtained from n_parallel (plus one,
to have an extra sequence to dedicate to the system prompt),
but there might be a better way to do this which won't also
make the main example use 2 cells even if only 1 is really used.
(for this specific case, --parallel 0 helps)
Simultaneous sequence processing will probably require changes to
ggml_ssm_scan, and possibly a new operator for the conv step.
* mamba : support llama_kv_cache_seq_cp
This (mis)uses the logic around K shifts, because tokens in a state
can't be shifted anyway, and because inp_K_shift has the right shape and type.
Using ggml_get_rows is a nice way to do copies, but copy chains can't work.
Fortunately, copy chains don't really seem to be used in the examples.
Each KV cell is dedicated to the sequence ID corresponding to its own index.
* mamba : use a state mask
It's cleaner than the previous heuristic of
checking for the pos of the first token in the batch.
inp_KQ_mask could not be re-used for this, because it has the wrong shape
and because it seems more suited to the next step of
simultaneous sequence processing (helping with the problem of
remembering which token belongs to which sequence(s)/state(s)).
* llama : replace the usage of n_ctx with kv_self.size in many places
* mamba : use n_tokens directly instead of n_tok
* mamba : in comments, properly refer to KV cells instead of slots
* mamba : reduce memory usage of ggml_ssm_scan
From 290.37 MiB to 140.68 MiB of CPU compute buffer size
with Mamba 3B with a batch size of 512.
The result tensor of ggml_ssm_scan was previously a big part
of the CPU compute buffer size. To make it smaller,
it does not contain the intermediate ssm states anymore.
Both y and the last ssm state are combined in the result tensor,
because it seems only a single tensor can be returned by an operator
with the way the graph is built.
* mamba : simultaneous sequence processing
A batch can now contain tokens from multiple sequences.
This is necessary for at least the parallel example, the server example,
and the HellaSwag test in the perplexity example.
However, for this to be useful, uses of llama_kv_cache_seq_rm/cp
will need to be changed to work on whole sequences.
* ggml : add ggml_ssm_conv as a new operator for the conv step of Mamba
This operator makes it possible to use and update the correct states
for each token of the batch in the same way as ggml_ssm_scan.
Other solutions which use existing operators would need loops which would
add too many nodes to the graph (at least the ones I thought of).
Using this operator further reduces the size of the CPU compute buffer
from 140.68 MiB to 103.20 MiB with Mamba 3B with a batch size of 512.
And (at least on CPU), it's a bit faster than before.
Note that "ggml_ssm_conv" is probably not the most appropriate name,
and it could be changed if a better one is found.
* llama : add inp_s_seq as a new input tensor
The most convenient implementation to select the correct state (for Mamba)
for each token is to directly get the correct index from a tensor.
This is why inp_s_seq is storing int32_t and not floats.
The other, less convenient way to select the correct state would be
to have inp_KQ_mask contain 1.0f for each state used by a token
and 0.0f otherwise. This complicates quickly fetching the first used
state of a token, and is also less efficient because a whole row
of the mask would always need to be read for each token.
Using indexes makes it easy to stop searching when there are
no more sequences for a token, and the first sequence assigned
is always very quickly available (it's the first element of each row).
* mamba : support llama_kv_cache_seq_cp copy chains
* mamba : support shifting and dividing the kv cache pos
* mamba : make the server and parallel examples work with whole sequences
A seq_id is dedicated to the system prompt in both cases.
* llama : make llama_kv_cache_seq_rm return whether it succeeded or not
* mamba : dedicate an input tensor for state copy indices
This is cleaner and makes it easier to adapt when/if token positions
(and by extension, inp_K_shift) are no longer integers.
* mamba : adapt perplexity, batched, and batched-bench examples
* perplexity : limit the max number of sequences
This adapts to what the loaded model can provide.
* llama : add llama_n_max_seq to get the upper limit for seq_ids
Used by the perplexity example.
* batched : pass n_parallel to the model's context params
This should have been there already, but it wasn't.
* batched-bench : reserve sequences to support Mamba
* batched-bench : fix tokens being put in wrong sequences
Generation quality isn't what's measured in there anyway,
but at least using the correct sequences avoids using non-consecutive
token positions.
* mamba : stop abusing attention metadata
This breaks existing converted-to-GGUF Mamba models,
but will allow supporting mixed architectures like MambaFormer
without needing to break Mamba models.
This will also allow changing the size of Mamba's states
without having to reconvert models in the future.
(e.g. using something else than d_conv - 1 columns for the conv_states
will not require breaking existing converted Mamba models again)
* gguf-py : add new KV metadata key-value pairs for Mamba
* llama : add new metadata key-value pairs for Mamba
* llama : guard against divisions by zero when n_head is 0
* mamba : rename "unlimited" KV cache property to "recurrent"
* mamba : more correctly update the "used" field of the KV cache
* ggml : in ggml_ssm_scan, use a threshold for soft_plus
This is how the official Mamba implementation does it,
and it's also what torch.nn.Softplus does.
* convert : for Mamba, fallback to internal NeoX tokenizer
The resulting models are exactly the same
as if the tokenizer.json and tokenizer_config.json of GPT-NeoX were there.
* mamba : support state saving and restoring
* ggml : implicitly pass src tensors through dst for Mamba-related ops
* mamba : clarify some comments
* server : fix cache_tokens not getting correctly resized
Otherwise, when the "we have to evaluate at least 1 token" special case
was triggered, an extra token was kept in cache_tokens even if it was
removed from the KV cache.
For Mamba, this caused useless prompt reprocessing when the previous
request triggered the above case.
* convert-hf : support new metadata keys for Mamba
For the models available at
https://huggingface.co/collections/state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406
* mamba : rename metadata to be more similar to transformers library
This breaks existing converted-to-GGUF models,
but the metadata names are more "standard".
* mamba : support mamba-*-hf models
These models share their token_embd.weight with their output.weight
* mamba : add missing spaces
This is purely a formatting change.
* convert-hf : omit output.weight when identical with token_embd.weight
Only for Mamba for now, but it might be relevant for other models eventually.
Most Mamba models actually share these two tensors, albeit implicitly.
* readme : add Mamba to supported models, and add recent API changes
* mamba : move state_seq and state_mask views outside layer loop
A few tensors were also missing `struct` in front of `ggml_tensor`.
2024-03-08 23:31:00 +01:00
- [x] [Mamba ](https://github.com/state-spaces/mamba )
2024-04-25 15:52:28 +02:00
- [x] [Grok-1 ](https://huggingface.co/keyfan/grok-1-hf )
2024-03-29 14:37:03 +01:00
- [x] [Xverse ](https://huggingface.co/models?search=xverse )
2024-04-25 15:52:28 +02:00
- [x] [Command-R models ](https://huggingface.co/models?search=CohereForAI/c4ai-command-r )
2024-04-03 20:05:10 +02:00
- [x] [SEA-LION ](https://huggingface.co/models?search=sea-lion )
2024-04-07 19:33:59 +02:00
- [x] [GritLM-7B ](https://huggingface.co/GritLM/GritLM-7B ) + [GritLM-8x7B ](https://huggingface.co/GritLM/GritLM-8x7B )
2024-04-19 11:35:54 +02:00
- [x] [OLMo ](https://allenai.org/olmo )
2024-11-26 21:55:29 +01:00
- [x] [OLMo 2 ](https://allenai.org/olmo )
2024-09-16 08:47:37 +02:00
- [x] [OLMoE ](https://huggingface.co/allenai/OLMoE-1B-7B-0924 )
2024-08-05 07:54:10 +02:00
- [x] [Granite models ](https://huggingface.co/collections/ibm-granite/granite-code-models-6624c5cec322e4c148c8b330 )
2024-05-23 14:12:43 +02:00
- [x] [GPT-NeoX ](https://github.com/EleutherAI/gpt-neox ) + [Pythia ](https://github.com/EleutherAI/pythia )
2024-08-05 07:54:10 +02:00
- [x] [Snowflake-Arctic MoE ](https://huggingface.co/collections/Snowflake/arctic-66290090abe542894a5ac520 )
- [x] [Smaug ](https://huggingface.co/models?search=Smaug )
- [x] [Poro 34B ](https://huggingface.co/LumiOpen/Poro-34B )
- [x] [Bitnet b1.58 models ](https://huggingface.co/1bitLLM )
- [x] [Flan T5 ](https://huggingface.co/models?search=flan-t5 )
- [x] [Open Elm models ](https://huggingface.co/collections/apple/openelm-instruct-models-6619ad295d7ae9f868b759ca )
2024-07-08 07:57:19 +02:00
- [x] [ChatGLM3-6b ](https://huggingface.co/THUDM/chatglm3-6b ) + [ChatGLM4-9b ](https://huggingface.co/THUDM/glm-4-9b )
2024-08-05 07:54:10 +02:00
- [x] [SmolLM ](https://huggingface.co/collections/HuggingFaceTB/smollm-6695016cad7167254ce15966 )
2024-08-16 08:35:18 +02:00
- [x] [EXAONE-3.0-7.8B-Instruct ](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct )
2024-08-21 10:06:36 +02:00
- [x] [FalconMamba Models ](https://huggingface.co/collections/tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a )
2024-09-12 02:29:53 +02:00
- [x] [Jais ](https://huggingface.co/inceptionai/jais-13b-chat )
2024-10-01 19:18:46 +02:00
- [x] [Bielik-11B-v2.3 ](https://huggingface.co/collections/speakleash/bielik-11b-v23-66ee813238d9b526a072408a )
2024-10-22 12:33:37 +02:00
- [x] [RWKV-6 ](https://github.com/BlinkDL/RWKV-LM )
2023-12-14 08:38:49 +01:00
2024-11-30 08:47:07 +01:00
**Multimodal:**
2023-12-14 08:38:49 +01:00
2024-02-28 09:39:39 +01:00
- [x] [LLaVA 1.5 models ](https://huggingface.co/collections/liuhaotian/llava-15-653aac15d994e992e2677a7e ), [LLaVA 1.6 models ](https://huggingface.co/collections/liuhaotian/llava-16-65b9e40155f60fd046a5ccf2 )
2024-02-05 15:55:10 +01:00
- [x] [BakLLaVA ](https://huggingface.co/models?search=SkunkworksAI/Bakllava )
2023-12-14 08:38:49 +01:00
- [x] [Obsidian ](https://huggingface.co/NousResearch/Obsidian-3B-V0.5 )
- [x] [ShareGPT4V ](https://huggingface.co/models?search=Lin-Chen/ShareGPT4V )
2024-01-25 21:14:32 +01:00
- [x] [MobileVLM 1.7B/3B models ](https://huggingface.co/models?search=mobileVLM )
2024-02-06 15:06:48 +01:00
- [x] [Yi-VL ](https://huggingface.co/models?search=Yi-VL )
2024-04-25 15:52:28 +02:00
- [x] [Mini CPM ](https://huggingface.co/models?search=MiniCPM )
2024-05-10 08:41:10 +02:00
- [x] [Moondream ](https://huggingface.co/vikhyatk/moondream2 )
2024-05-23 16:43:18 +02:00
- [x] [Bunny ](https://github.com/BAAI-DCAI/Bunny )
2023-10-17 20:13:21 +02:00
2024-11-30 08:47:07 +01:00
< / details >
< details >
< summary > Bindings< / summary >
2023-04-05 17:56:20 +02:00
- Python: [abetlen/llama-cpp-python ](https://github.com/abetlen/llama-cpp-python )
- Go: [go-skynet/go-llama.cpp ](https://github.com/go-skynet/go-llama.cpp )
2023-10-22 20:16:43 +02:00
- Node.js: [withcatai/node-llama-cpp ](https://github.com/withcatai/node-llama-cpp )
2024-01-07 21:24:11 +01:00
- JS/TS (llama.cpp server client): [lgrammel/modelfusion ](https://modelfusion.dev/integration/model-provider/llamacpp )
2024-09-23 17:58:17 +02:00
- JS/TS (Programmable Prompt Engine CLI): [offline-ai/cli ](https://github.com/offline-ai/cli )
2024-02-09 11:17:00 +01:00
- JavaScript/Wasm (works in browser): [tangledgroup/llama-cpp-wasm ](https://github.com/tangledgroup/llama-cpp-wasm )
2024-03-16 16:42:08 +01:00
- Typescript/Wasm (nicer API, available on npm): [ngxson/wllama ](https://github.com/ngxson/wllama )
2023-04-17 21:34:35 +02:00
- Ruby: [yoshoku/llama_cpp.rb ](https://github.com/yoshoku/llama_cpp.rb )
2024-04-03 19:53:37 +02:00
- Rust (more features): [edgenai/llama_cpp-rs ](https://github.com/edgenai/llama_cpp-rs )
2024-01-28 09:30:44 +01:00
- Rust (nicer API): [mdrokz/rust-llama.cpp ](https://github.com/mdrokz/rust-llama.cpp )
- Rust (more direct bindings): [utilityai/llama-cpp-rs ](https://github.com/utilityai/llama-cpp-rs )
2023-05-12 07:39:40 +02:00
- C#/.NET: [SciSharp/LLamaSharp ](https://github.com/SciSharp/LLamaSharp )
2024-10-20 18:25:41 +02:00
- C#/VB.NET (more features - community license): [LM-Kit.NET ](https://docs.lm-kit.com/lm-kit-net/index.html )
2023-06-26 21:47:59 +02:00
- Scala 3: [donderom/llm4s ](https://github.com/donderom/llm4s )
2023-08-18 21:39:22 +02:00
- Clojure: [phronmophobic/llama.clj ](https://github.com/phronmophobic/llama.clj )
2023-08-29 11:30:10 +02:00
- React Native: [mybigday/llama.rn ](https://github.com/mybigday/llama.rn )
2023-09-01 15:36:14 +02:00
- Java: [kherud/java-llama.cpp ](https://github.com/kherud/java-llama.cpp )
2023-12-22 07:49:54 +01:00
- Zig: [deins/llama.cpp.zig ](https://github.com/Deins/llama.cpp.zig )
2024-01-20 09:05:43 +01:00
- Flutter/Dart: [netdur/llama_cpp_dart ](https://github.com/netdur/llama_cpp_dart )
2024-11-13 12:17:10 +01:00
- Flutter: [xuegao-tzx/Fllama ](https://github.com/xuegao-tzx/Fllama )
2024-03-27 08:08:59 +01:00
- PHP (API bindings and features built on top of llama.cpp): [distantmagic/resonance ](https://github.com/distantmagic/resonance ) [(more info) ](https://github.com/ggerganov/llama.cpp/pull/6326 )
2024-07-07 15:21:37 +02:00
- Guile Scheme: [guile_llama_cpp ](https://savannah.nongnu.org/projects/guile-llama-cpp )
2024-10-15 10:20:34 +02:00
- Swift [srgtuszy/llama-cpp-swift ](https://github.com/srgtuszy/llama-cpp-swift )
2024-10-17 08:57:14 +02:00
- Swift [ShenghaiWang/SwiftLlama ](https://github.com/ShenghaiWang/SwiftLlama )
2023-04-05 17:56:20 +02:00
2024-11-30 08:47:07 +01:00
< / details >
< details >
< summary > UIs< / summary >
*(to have a project listed here, it should clearly state that it depends on `llama.cpp` )*
2023-04-05 17:56:20 +02:00
2024-11-29 17:45:08 +01:00
- [AI Sublime Text plugin ](https://github.com/yaroslavyaroslav/OpenAI-sublime-text ) (MIT)
- [cztomsik/ava ](https://github.com/cztomsik/ava ) (MIT)
- [Dot ](https://github.com/alexpinel/Dot ) (GPL)
- [eva ](https://github.com/ylsdamxssjxxdd/eva ) (MIT)
- [iohub/collama ](https://github.com/iohub/coLLaMA ) (Apache-2.0)
2024-02-05 15:55:10 +01:00
- [janhq/jan ](https://github.com/janhq/jan ) (AGPL)
2024-11-29 17:45:08 +01:00
- [KanTV ](https://github.com/zhouwg/kantv?tab=readme-ov-file ) (Apache-2.0)
- [KodiBot ](https://github.com/firatkiral/kodibot ) (GPL)
2024-11-30 08:47:07 +01:00
- [llama.vim ](https://github.com/ggml-org/llama.vim ) (MIT)
2024-11-29 17:45:08 +01:00
- [LARS ](https://github.com/abgulati/LARS ) (AGPL)
- [Llama Assistant ](https://github.com/vietanhdev/llama-assistant ) (GPL)
- [LLMFarm ](https://github.com/guinmoon/LLMFarm?tab=readme-ov-file ) (MIT)
- [LLMUnity ](https://github.com/undreamai/LLMUnity ) (MIT)
2024-02-05 15:55:10 +01:00
- [LMStudio ](https://lmstudio.ai/ ) (proprietary)
2024-02-21 15:39:10 +01:00
- [LocalAI ](https://github.com/mudler/LocalAI ) (MIT)
2024-02-05 15:55:10 +01:00
- [LostRuins/koboldcpp ](https://github.com/LostRuins/koboldcpp ) (AGPL)
2024-11-29 17:45:08 +01:00
- [MindMac ](https://mindmac.app ) (proprietary)
- [MindWorkAI/AI-Studio ](https://github.com/MindWorkAI/AI-Studio ) (FSL-1.1-MIT)
- [Mobile-Artificial-Intelligence/maid ](https://github.com/Mobile-Artificial-Intelligence/maid ) (MIT)
- [Mozilla-Ocho/llamafile ](https://github.com/Mozilla-Ocho/llamafile ) (Apache-2.0)
- [nat/openplayground ](https://github.com/nat/openplayground ) (MIT)
- [nomic-ai/gpt4all ](https://github.com/nomic-ai/gpt4all ) (MIT)
- [ollama/ollama ](https://github.com/ollama/ollama ) (MIT)
2024-02-05 15:55:10 +01:00
- [oobabooga/text-generation-webui ](https://github.com/oobabooga/text-generation-webui ) (AGPL)
2024-11-29 17:45:08 +01:00
- [PocketPal AI ](https://github.com/a-ghorbani/pocketpal-ai ) (MIT)
- [psugihara/FreeChat ](https://github.com/psugihara/FreeChat ) (MIT)
- [ptsochantaris/emeltal ](https://github.com/ptsochantaris/emeltal ) (MIT)
2024-02-05 15:55:10 +01:00
- [pythops/tenere ](https://github.com/pythops/tenere ) (AGPL)
2024-11-29 17:45:08 +01:00
- [ramalama ](https://github.com/containers/ramalama ) (MIT)
- [semperai/amica ](https://github.com/semperai/amica ) (MIT)
- [withcatai/catai ](https://github.com/withcatai/catai ) (MIT)
2024-04-17 14:47:50 +02:00
2024-11-30 08:47:07 +01:00
< / details >
2024-03-28 21:56:03 +01:00
2024-11-30 08:47:07 +01:00
< details >
< summary > Tools< / summary >
2024-05-26 14:09:42 +02:00
- [akx/ggify ](https://github.com/akx/ggify ) –
2024-09-28 14:07:14 +02:00
- [akx/ollama-dl ](https://github.com/akx/ollama-dl ) –
2024-07-01 18:48:34 +02:00
- [crashr/gppm ](https://github.com/crashr/gppm ) –
2024-08-12 14:45:50 +02:00
- [gpustack/gguf-parser ](https://github.com/gpustack/gguf-parser-go/tree/main/cmd/gguf-parser ) - review/check the GGUF file and estimate the memory usage
2024-11-30 08:47:07 +01:00
- [Styled Lines ](https://marketplace.unity.com/packages/tools/generative-ai/styled-lines-llama-cpp-model-292902 ) (proprietary licensed, async wrapper of inference part for game development in Unity3d with pre-built Mobile and Web platform wrappers and a model example)
2024-05-26 14:09:42 +02:00
2024-11-30 08:47:07 +01:00
< / details >
< details >
< summary > Infrastructure< / summary >
2024-07-01 19:13:22 +02:00
- [Paddler ](https://github.com/distantmagic/paddler ) - Stateful load balancer custom-tailored for llama.cpp
2024-08-12 14:45:50 +02:00
- [GPUStack ](https://github.com/gpustack/gpustack ) - Manage GPU clusters for running LLMs
2024-10-20 18:01:34 +02:00
- [llama_cpp_canister ](https://github.com/onicai/llama_cpp_canister ) - llama.cpp as a smart contract on the Internet Computer, using WebAssembly
2024-07-01 19:13:22 +02:00
2024-11-30 08:47:07 +01:00
< / details >
2023-03-10 20:47:46 +01:00
2024-07-05 18:08:32 +02:00
< details >
2024-11-30 08:47:07 +01:00
< summary > Games< / summary >
2023-03-10 20:47:46 +01:00
2024-11-30 08:47:07 +01:00
- [Lucy's Labyrinth ](https://github.com/MorganRO8/Lucys_Labyrinth ) - A simple maze game where agents controlled by an AI model will try to trick you.
2023-03-10 20:47:46 +01:00
2024-07-05 18:08:32 +02:00
< / details >
2024-11-30 08:47:07 +01:00
## Supported backends
| Backend | Target devices |
| --- | --- |
| [Metal ](./docs/build.md#metal-build ) | Apple Silicon |
| [BLAS ](./docs/build.md#blas-build ) | All |
| [BLIS ](./docs/backend/BLIS.md ) | All |
| [SYCL ](./docs/backend/SYCL.md ) | Intel and Nvidia GPU |
| [MUSA ](./docs/build.md#musa ) | Moore Threads MTT GPU |
| [CUDA ](./docs/build.md#cuda ) | Nvidia GPU |
| [hipBLAS ](./docs/build.md#hipblas ) | AMD GPU |
| [Vulkan ](./docs/build.md#vulkan ) | GPU |
| [CANN ](./docs/build.md#cann ) | Ascend NPU |
2024-07-05 18:08:32 +02:00
2024-11-30 08:47:07 +01:00
## Building and usage
2023-03-10 23:51:46 +01:00
2024-11-30 08:47:07 +01:00
The main product of this project is the `llama` library. Its C-style interface can be found in [include/llama.h ](include/llama.h ).
The project also includes many example programs and tools using the `llama` library. The examples range from simple, minimal code snippets to sophisticated sub-projects such as an OpenAI-compatible HTTP server. Possible methods for obtaining the binaries:
2023-03-10 23:51:46 +01:00
2024-11-30 08:47:07 +01:00
- Clone this repository and build locally, see [how to build ](./docs/build.md )
- On MacOS or Linux, install `llama.cpp` via [brew, flox or nix ](./docs/install.md )
- Use a Docker image, see [documentation for Docker ](./docs/docker.md )
- Download pre-built binaries from [releases ](https://github.com/ggerganov/llama.cpp/releases )
### Obtaining and quantizing models
The [Hugging Face ](https://huggingface.co ) platform hosts a [number of LLMs ](https://huggingface.co/models?library=gguf&sort=trending ) compatible with `llama.cpp` :
- [Trending ](https://huggingface.co/models?library=gguf&sort=trending )
- [LLaMA ](https://huggingface.co/models?sort=trending&search=llama+gguf )
2024-07-05 18:08:32 +02:00
2024-11-30 08:47:07 +01:00
After downloading a model, use the CLI tools to run it locally - see below.
2023-03-10 20:47:46 +01:00
2024-11-30 08:47:07 +01:00
`llama.cpp` requires the model to be stored in the [GGUF ](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md ) file format. Models in other data formats can be converted to GGUF using the `convert_*.py` Python scripts in this repo.
2023-04-13 15:43:22 +02:00
2024-11-30 08:47:07 +01:00
The Hugging Face platform provides a variety of online tools for converting, quantizing and hosting models with `llama.cpp` :
2023-04-26 22:03:03 +02:00
2024-11-30 08:47:07 +01:00
- Use the [GGUF-my-repo space ](https://huggingface.co/spaces/ggml-org/gguf-my-repo ) to convert to GGUF format and quantize model weights to smaller sizes
- Use the [GGUF-my-LoRA space ](https://huggingface.co/spaces/ggml-org/gguf-my-lora ) to convert LoRA adapters to GGUF format (more info: https://github.com/ggerganov/llama.cpp/discussions/10123)
- Use the [GGUF-editor space ](https://huggingface.co/spaces/CISCai/gguf-editor ) to edit GGUF meta data in the browser (more info: https://github.com/ggerganov/llama.cpp/discussions/9268)
- Use the [Inference Endpoints ](https://ui.endpoints.huggingface.co/ ) to directly host `llama.cpp` in the cloud (more info: https://github.com/ggerganov/llama.cpp/discussions/9669)
2023-04-26 22:03:03 +02:00
2024-11-30 08:47:07 +01:00
To learn more about model quantization, [read this documentation ](./examples/quantize/README.md )
### Using the `llama-cli` tool
Run a basic text completion:
2023-03-10 20:47:46 +01:00
2024-07-05 18:08:32 +02:00
```bash
llama-cli -m your_model.gguf -p "I believe the meaning of life is" -n 128
2024-05-30 16:58:15 +02:00
2024-07-05 18:08:32 +02:00
# Output:
# I believe the meaning of life is to find your own truth and to live in accordance with it. For me, this means being true to myself and following my passions, even if they don't align with societal expectations. I think that's what I love about yoga –
2024-05-30 16:58:15 +02:00
```
2024-06-17 17:37:55 +02:00
2024-07-05 18:08:32 +02:00
See [this page ](./examples/main/README.md ) for a full list of parameters.
2024-06-17 17:37:55 +02:00
2024-07-05 18:08:32 +02:00
### Conversation mode
2024-06-17 17:37:55 +02:00
2024-11-30 08:47:07 +01:00
Run `llama-cli` in conversation/chat mode by passing the `-cnv` parameter:
2024-06-17 17:37:55 +02:00
2024-07-05 18:08:32 +02:00
```bash
llama-cli -m your_model.gguf -p "You are a helpful assistant" -cnv
2024-06-17 17:37:55 +02:00
2024-07-05 18:08:32 +02:00
# Output:
# > hi, who are you?
# Hi there! I'm your helpful assistant! I'm an AI-powered chatbot designed to assist and provide information to users like you. I'm here to help answer your questions, provide guidance, and offer support on a wide range of topics. I'm a friendly and knowledgeable AI, and I'm always happy to help with anything you need. What's on your mind, and how can I assist you today?
#
# > what is 1+1?
# Easy peasy! The answer to 1+1 is... 2!
2024-06-17 17:37:55 +02:00
```
2023-05-20 16:58:31 +02:00
2024-07-05 18:08:32 +02:00
By default, the chat template will be taken from the input model. If you want to use another chat template, pass `--chat-template NAME` as a parameter. See the list of [supported templates ](https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template )
2024-05-05 07:21:46 +02:00
2023-04-13 15:43:22 +02:00
```bash
2024-11-30 08:47:07 +01:00
llama-cli -m your_model.gguf -p "You are a helpful assistant" -cnv --chat-template chatml
2024-02-07 07:21:30 +01:00
```
2023-09-21 21:00:24 +02:00
2024-07-05 18:08:32 +02:00
You can also use your own template via in-prefix, in-suffix and reverse-prompt parameters:
2023-09-21 21:00:24 +02:00
2024-02-07 07:21:30 +01:00
```bash
2024-11-30 08:47:07 +01:00
llama-cli -m your_model.gguf -p "You are a helpful assistant" -cnv --in-prefix 'User: ' --reverse-prompt 'User:'
2023-05-24 08:24:01 +02:00
```
2023-08-23 03:01:57 +02:00
### Constrained output with grammars
2024-11-30 08:47:07 +01:00
`llama.cpp` can constrain the output of the model via custom grammars. For example, you can force the model to output only JSON:
2023-08-23 03:01:57 +02:00
```bash
2024-11-30 08:47:07 +01:00
llama-cli -m your_model.gguf -n 256 --grammar-file grammars/json.gbnf -p 'Request: schedule a call at 8pm; Command:'
2023-08-23 03:01:57 +02:00
```
The `grammars/` folder contains a handful of sample grammars. To write your own, check out the [GBNF Guide ](./grammars/README.md ).
2024-11-30 08:47:07 +01:00
For authoring more complex JSON grammars, check out https://grammar.intrinsiclabs.ai/
2023-07-28 03:14:11 +02:00
2024-11-30 08:47:07 +01:00
### Web server (`llama-server`)
2023-07-28 03:14:11 +02:00
2024-11-30 08:47:07 +01:00
The [llama-server ](./examples/server/README.md ) is a lightweight [OpenAI API ](https://github.com/openai/openai-openapi ) compatible HTTP server that can be used to serve local models and easily connect them to existing clients.
2023-03-20 21:14:06 +01:00
2024-11-30 08:47:07 +01:00
Example usage:
2023-07-07 20:25:25 +02:00
2024-11-30 08:47:07 +01:00
```bash
llama-server -m your_model.gguf --port 8080
2023-07-07 20:25:25 +02:00
2024-11-30 08:47:07 +01:00
# Basic web UI can be accessed via browser: http://localhost:8080
# Chat completion endpoint: http://localhost:8080/v1/chat/completions
```
2023-07-07 20:25:25 +02:00
2024-07-05 18:08:32 +02:00
### Perplexity (measuring model quality)
2023-07-07 20:25:25 +02:00
2024-11-30 08:47:07 +01:00
Use the `llama-perplexity` tool to measure perplexity over a given prompt (lower perplexity is better).
2024-07-05 18:08:32 +02:00
For more information, see [https://huggingface.co/docs/transformers/perplexity ](https://huggingface.co/docs/transformers/perplexity ).
2023-07-07 20:25:25 +02:00
2024-07-05 18:08:32 +02:00
To learn more how to measure perplexity using llama.cpp, [read this documentation ](./examples/perplexity/README.md )
2023-07-07 20:25:25 +02:00
2024-07-05 18:08:32 +02:00
## Contributing
2023-03-13 08:42:26 +01:00
2023-03-13 18:21:51 +01:00
- Contributors can open PRs
2023-03-16 07:55:13 +01:00
- Collaborators can push to branches in the `llama.cpp` repo and merge PRs into the `master` branch
2023-03-13 08:42:26 +01:00
- Collaborators will be invited based on contributions
2024-09-29 13:38:18 +02:00
- Any help with managing issues, PRs and projects is very appreciated!
2024-07-05 08:09:47 +02:00
- See [good first issues ](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22 ) for tasks suitable for first contributions
- Read the [CONTRIBUTING.md ](CONTRIBUTING.md ) for more information
2023-03-17 19:30:04 +01:00
- Make sure to read this: [Inference at the edge ](https://github.com/ggerganov/llama.cpp/discussions/205 )
2023-03-23 09:46:58 +01:00
- A bit of backstory for those who are interested: [Changelog podcast ](https://changelog.com/podcast/532 )
2023-03-13 08:42:26 +01:00
2024-11-17 09:06:34 +01:00
## Other documentation
2023-04-05 17:56:20 +02:00
2024-06-13 01:41:52 +02:00
- [main (cli) ](./examples/main/README.md )
2023-07-09 09:38:42 +02:00
- [server ](./examples/server/README.md )
2024-07-05 18:08:32 +02:00
- [GBNF grammars ](./grammars/README.md )
2024-11-17 09:06:34 +01:00
**Development documentation**
2024-07-05 18:08:32 +02:00
- [How to build ](./docs/build.md )
- [Running on Docker ](./docs/docker.md )
- [Build on Android ](./docs/android.md )
2024-07-09 20:58:44 +02:00
- [Performance troubleshooting ](./docs/development/token_generation_performance_tips.md )
2023-07-09 09:38:42 +02:00
- [GGML tips & tricks ](https://github.com/ggerganov/llama.cpp/wiki/GGML-Tips-&-Tricks )
2024-07-06 19:01:23 +02:00
**Seminal papers and background on the models**
If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:
- LLaMA:
- [Introducing LLaMA: A foundational, 65-billion-parameter large language model ](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/ )
- [LLaMA: Open and Efficient Foundation Language Models ](https://arxiv.org/abs/2302.13971 )
- GPT-3
- [Language Models are Few-Shot Learners ](https://arxiv.org/abs/2005.14165 )
- GPT-3.5 / InstructGPT / ChatGPT:
- [Aligning language models to follow instructions ](https://openai.com/research/instruction-following )
- [Training language models to follow instructions with human feedback ](https://arxiv.org/abs/2203.02155 )
