Commit Graph

3326 Commits

Author SHA1 Message Date
Giuseppe Scrivano
5442939fcc
llama : support small Granite models (#7481)
* Add optional MLP bias for Granite models

Add optional MLP bias for ARCH_LLAMA to support Granite models.
Partially addresses ggerganov/llama.cpp/issues/7116
Still needs some more changes to properly support Granite.

* llama: honor add_space_prefix from the model configuration

propagate the add_space_prefix configuration from the HF model
configuration to the gguf file and honor it with the gpt2 tokenizer.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

* llama: add support for small granite models

it works only for the small models 3b and 8b.

The convert-hf-to-gguf.py script uses the vocabulary size of the
granite models to detect granite and set the correct configuration.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

---------

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
Co-authored-by: Steffen Roecker <sroecker@redhat.com>
2024-05-28 21:49:49 +03:00
k.h.lai
56411a950f
vulkan: properly initialize vulkan devices for LLAMA_SPLIT_MODE_NONE (#7552) 2024-05-28 19:25:08 +02:00
Radoslav Gerganov
2b737caae1
rpc : resource management rework (#7562)
* rpc : resource management rework

* address review comments
2024-05-28 18:13:36 +03:00
fairydreaming
ee3dff6b8e
Add support for DeepseekV2ForCausalLM (#7519)
* common : increase max number of experts to 160

* common : add tensors ATTN_Q_A, ATTN_Q_A_NORM, ATTN_Q_B, ATTN_KV_A_MQA, ATTN_KV_A_NORM, ATTN_KV_B needed by DeepSeek-V2 MLA (multi-head latent attention) architecture

* common : add model header parameters: leading_dense_block_count, expert_feed_forward_length, expert_shared_count, expert_weights_scale, attention.q_lora_rank, attention.kv_lora_rank, rope.scaling.yarn_log_multiplier

* convert-hf : add model conversion support for DeepseekV2ForCausalLM

* llama : add model types for DeepSeek-V2 and DeepSeek-V2-Lite models

* llama : add two new llm_build_moe_ffn() arguments: scale_w (whether to scale weights of selected MoE experts) and w_scale (numerical value of the scaling factor)

* llama : add inference support for LLM_ARCH_DEEPSEEK2

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2024-05-28 17:07:05 +02:00
Georgi Gerganov
edc29433fa
tests : fix test-tokenizer-0.sh 2024-05-28 15:04:09 +03:00
Georgi Gerganov
8b99e2aa66
llama : handle unknown utf8 bytes (#7588) 2024-05-28 13:55:35 +03:00
Brian
271ff3fc44
github: add refactor to issue template (#7561)
* github: add refactor issue template [no ci]

* Update 07-refactor.yml
2024-05-28 20:27:27 +10:00
Neo Zhang
e2b065071c
[SYCL]fix ggml_sycl_mul_mat_id() to match the change of api (#7436)
* fix mul_mat_id to match the change of api

* rm comment

* rm unused or duplicated code, rename as review comment
2024-05-28 10:53:37 +01:00
Georgi Gerganov
0548a4187f
ggml : generalize GGML_OP_CONCAT (#7563)
* ggml : generalize GGML_OP_CONCAT (WIP)

ggml-ci

* tests : add dim != 2 tests

* metal : generalize concat kernel

* tests : naming

* cuda : generalize concat kernel

ggml-ci

* sycl : add warning and assert

* ggml : fix op params handling

* metal : bugfix kernel

ggml-ci

* ggml : reimplement CPU and Metal

* cuda : add asserts

ggml-ci

* ggml : fix ptrs

ggml-ci
2024-05-28 11:04:19 +03:00
mgroeber9110
9335b969e8
server: do not remove whitespace at the start of a completion chunk (#7524) 2024-05-28 14:55:51 +10:00
Nathan Epstein
c41767154e
Markdownish code block fix (#7571)
* markdownish codeblock fix

* updating regexes
2024-05-28 14:41:14 +10:00
Ikko Eltociear Ashimine
74b239b3d5
llava : update clip.h (#7580)
overriden -> overridden
2024-05-28 12:48:16 +10:00
Djip007
852aafb163
update HIP_UMA #7399 (#7414)
* update HIP_UMA #7399

add use of hipMemAdviseSetCoarseGrain when LLAMA_HIP_UMA is enable.
- get x2 on prompte eval and x1.5 on token gen with rocm6.0 on ryzen 7940HX iGPU (780M/gfx1103)

* simplify code, more consistent style

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-05-28 01:40:47 +02:00
kunnis
0136966daf
adding in x64 targets to cmake presets (#7574) 2024-05-28 01:40:12 +02:00
Johannes Gäßler
10b1e45876
make: add --device-debug to NVCC debug flags (#7542) 2024-05-27 19:34:40 +02:00
agray3
197c00681b
Allow multiple copy function pointers for CUDA graph kernel param updates (#7565)
CUDA graphs require parameter updates to kernels associated with
GGML_OP_CPY nodes. Previously the implementation only checked for a
single CUDA kernel in such nodes, but this caused a bug in cases where
2 such kernels exist. This fixes the issue by using a vector to allow
multiple function pointers to be stored and checked against.

Fixes #7942
2024-05-27 19:33:42 +02:00
AidanBeltonS
95f84d5ce8
Fix q_xxs using mul_mat_q (#7459) 2024-05-27 22:04:51 +05:30
AidanBeltonS
5487593bc7
Add freq factors (#7495) 2024-05-27 18:04:09 +05:30
Georgi Gerganov
1d8fca72ae
metal : add GGML_OP_REPEAT kernels (#7557)
ggml-ci
2024-05-27 12:10:19 +03:00
Georgi Gerganov
62bfef5194
metal : disable FA kernel for HS=256 (#7556)
ggml-ci
2024-05-27 10:38:39 +03:00
Georgi Gerganov
eaf6e03174
llama : add comments about experimental flags (#7544) 2024-05-27 09:24:13 +03:00
Brian
d6ef0e77dd
github: add self sorted issue ticket forms (#7543)
* github: add self sorted issue ticket forms [no ci]

* github: consolidate BSD in bug issue ticket

* github: remove contact from bug ticket template [no ci]

* github: remove bios from os dropdown in bug report [no ci]
2024-05-27 10:54:30 +10:00
Georgi Gerganov
dff451cfa1
flake.lock: Update (#7540)
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/4a6b83b05df1a8bd7d99095ec4b4d271f2956b64?narHash=sha256-%2BNpbZRCRisUHKQJZF3CT%2Bxn14ZZQO%2BKjxIIanH3Pvn4%3D' (2024-05-17)
  → 'github:NixOS/nixpkgs/bfb7a882678e518398ce9a31a881538679f6f092?narHash=sha256-4zSIhSRRIoEBwjbPm3YiGtbd8HDWzFxJjw5DYSDy1n8%3D' (2024-05-24)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-26 08:54:56 -07:00
Brian
d298382ad9
main: replace --no-special with --special (#7534)
This also flips the default behavior of the output to not include control token by default.
2024-05-27 00:10:17 +10:00
Galunid
32a28217f4
Fix aya-23 conversion scripts (#7539) 2024-05-26 16:02:34 +02:00
Bartowski
c429b33beb
llama : add Smaug 70B support (#7402) 2024-05-26 15:28:35 +03:00
Aarni Koskela
9146d36fe7
Readme: add akx/ggify to tools (#1484) 2024-05-26 22:09:42 +10:00
HanishKVC
b9adcbbf92
SimpleChat Completion Mode flexibility and cleanup, Settings gMe, Optional sliding window (#7480)
* SimpleChat: A placeholder system prompt, Use usage msg in code

Just have a alert msg wrt needing javascript enabled in html. And
have usage message from js file. Update the usage message a bit.
So also enable switch session wrt setup_ui call.

Add a possible system prompt as a placeholder for the system-input.

* SimpleChat:CompletionMode: Allow control of Role: prefix

* SimpleChat:Completion: Avoid Role: prefix; Newline only in between

In completion mode

* avoid inserting Role: prefix before each role's message

* avoid inserting newline at the begin and end of the prompt
  message. However if there are multiple role messages, then
  insert newline when going from one role's message to the
  next role's message.

* SimpleChat:CompletionMode: Update readme/usage, trim textarea newline

Readme update wrt completion mode behavior.

Usage help updated wrt completion mode behavior.

When changing from input to textarea elment wrt user input, the last
newline at the end of the user input wrt textarea, was forgotten to be
filtered, this is fixed now. However if user wants to have a explicit
newline they can using shift+enter to insert a newline, that wont be
removed. The extra newline removal logic uses substring and keyup to
keep things simple and avoid some previously noted bugs wrt other
events in the key path as well as IME composition etal.

* SimpleChat:SC: Ensure proper clearing/reseting

previous logic would have cleared/reset the xchat, without doing
the same wrt iLastSys, thus leading to it pointing to a now non
existent role-content entry.

So if a user set a system prompt and used completion mode, it would
have done the half stupid clear, after the model response was got.
Inturn when user tries to send a new completion query, it would
inturn lead to handle_user_submit trying to add/update system prompt
if any, which will fail, bcas iLastSys will be still pointing to a
non existant entry.

This is fixed now, by having a proper clear helper wrt SC class.

* SimpleChat: Update usage note and readme a bit

* SimpleChat:Completion: clear any prev chat history at begining

Previously any chat history including model response to a completion
query would have got cleared, after showing the same to the user,
at the end of handle_user_submit, rather than at the begining.

This gave the flexibility that user could switch from chat mode
to completion mode and have the chat history till then sent to
the ai model, as part of the completion query. However this flow
also had the issue that, if user switches between different chat
sessions, after getting a completion response, they can no longer
see the completion query and its response that they had just got.

The new flow changes the clearing of chat history wrt completion
mode to the begining of handle_user_submit, so that user doesnt
lose the last completion mode query and response, till a new
completion mode query is sent to the model, even if they were to
switch between the chat sessions. At the same time the loss of
flexibility wrt converting previous chat history into being part
of the completion query implicitly doesnt matter, because now
the end user can enter multiline queries.

* SimpleChat:Try read json early, if available

For later

the server flow doesnt seem to be sending back data early, atleast
for the request (inc options) that is currently sent.

if able to read json data early on in future, as and when ai model
is generating data, then this helper needs to indirectly update
the chat div with the recieved data, without waiting for the
overall data to be available.

* SimpleChat: Rename the half asleep mis-spelled global var

* SimpleChat: Common chat request options from a global object

* SimpleChat: Update title, usage and readme a bit

Keep the title simple so that print file name doesnt have chars
that need to be removed.

Update readme wrt some of the new helpers and options.

Change Usage list to a list of lists, add few items and style it
to reduce the margin wrt lists.

* SimpleChat:ChatRequestOptions: max_tokens

As some times based on the query from the user, the ai model may get
into a run away kind of generation with repeatations etal, so adding
max_tokens to try and limit this run away behaviour, if possible.

* SimpleChat: Reduce max_tokens to be small but still sufficient

* SimpleChat: Consolidate global vars into gMe, Display to user

This allows the end user to see the settings used by the logic,
as well as allows users to change/update the settings if they
want to by using devel-tools/console

* SimpleChat:SlidingWindow: iRecentUserMsgCnt to limit context load

This is disabled by default. However if enabled, then in addition
to latest system message, only the last N user messages, after the
latest system message and its reponses from the ai model will be sent
to the ai-model, when querying for a new response.

This specified N also includes the latest user query.

* SimpleChat: placeholder based usage hint for user-in textarea

* SimpleChat: Try make user experience better, if possible

Reduce chat history context sent to the server/ai-model to be
just the system-prompt, prev-user-request-and-ai-response and
cur-user-request, instead of the previous full chat history.
This way if there is any response with garbage/repeatation, it
doesnt mess with things beyond the next question, in some ways.

Increase max_tokens to 1024, so that a relatively large previous
reponse doesnt eat up the space available wrt next query-response.
However dont forget that the server when started should also
be started with a model context size of 1k or more, to be on
safe side.

Add frequency and presence penalty fields set to 1.2 to the set
of fields sent to server along with the user query. So that
the model is partly set to try avoid repeating text in its
response.

* SimpleChat:Add n_predict (equiv max_tokens) for llamacpp server

The /completions endpoint of examples/server doesnt take max_tokens,
instead it takes the internal n_predict, for now add the same on
the client side, maybe later add max_tokens to /completions endpoint
handling.

* SimpleChat: Note about trying to keep things simple yet flexible
2024-05-26 10:56:34 +10:00
Georgi Gerganov
9588f196b1
train : change default FA argument (#7528) 2024-05-25 15:22:35 +03:00
Brian
3cbd23ed88
labeler: added Apple Metal detector (+Kompute) (#7529)
* labeler: added Apple Metal detector [no ci]

* labeler: add Kompute to detector [no ci]
2024-05-25 19:30:42 +10:00
Justine Tunney
00c6390793
main : don't print special tokens with --grammar (#6923)
* main : don't print special tokens with --grammar

The CLI interface was recently changed to print special control tokens
like the </s> stop message one. This token shouldn't be printed if the
grammar flag was passed, unless the grammar specifies it, because that
breaks shell-scriptability.

* main: use seperate stream for control characters

* main: use dprintf and add --ctrl-token-no-out and --ctrl-token-fd-out

* main: dprintf isn't part of the IEEE POSIX standard. Just use write().

* main: remove --ctrl-token-fd-out in favor for fcntl() based detection

* common.cpp: accidentally removed --interactive-first

* main: only merge stdout and control token if not in conversation or grammar mode

* main: rejig control token descriptor handling

* main: must check pipe status on very top of program

* main: renamed --no-special from  --ctrl-token-no-out and other refactoring

* main: refactor ctrl_token_no_out --> no_special

* llama: rename llama_token_is_control_token() to llama_token_is_control()

* main: remove special token file descriptor feature (#5)

---------

Co-authored-by: Brian <mofosyne@gmail.com>
2024-05-25 19:04:03 +10:00
Masaya, Kato
faa0e6979a
ggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot (#7433)
* Add SVE support for q4_0_q8_0 q8_0_q8_0

* remove ifdef
2024-05-25 11:42:31 +03:00
Elton Kola
9791f40258
android : module (#7502)
* move ndk code to a new library

* add gradle file
2024-05-25 11:11:33 +03:00
Xuan Son Nguyen
902184dd3a
fix missing slash in fs_get_cache_directory() (#7503)
* fix missing slash in fs_get_cache_directory()

* use LOCALAPPDATA for fs_get_cache_directory()

* better code style
2024-05-25 13:30:59 +10:00
Mikko Juola
57684331fc
Make tokenize CLI tool have nicer command line arguments. (#6188)
* Make tokenizer.cpp CLI tool nicer.

Before this commit, tokenize was a simple CLI tool like this:

  tokenize MODEL_FILENAME PROMPT [--ids]

This simple tool loads the model, takes the prompt, and shows the tokens
llama.cpp is interpreting.

This changeset makes the tokenize more sophisticated, and more useful
for debugging and troubleshooting:

  tokenize [-m, --model MODEL_FILENAME]
           [--ids]
           [--stdin]
           [--prompt]
           [-f, --file]
           [--no-bos]
           [--log-disable]

It also behaves nicer on Windows now, interpreting and rendering Unicode
from command line arguments and pipes no matter what code page the user
has set on their terminal.

* style fix: strlen(str) == 0 --> *str == 0

* Simplify tokenize.cpp; by getting rid of handling positional style arguments.

It must now be invoked with long --model, --prompt etc. arguments only.
Shortens the code.

* tokenize.cpp: iostream header no longer required

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: brian khuu <mofosyne@gmail.com>
2024-05-25 11:14:42 +10:00
compilade
b83bab15a5
gguf-py : fix and simplify quantized shape round-trip (#7483)
* gguf-py : fix and simplify quantized shape round-trip

* gguf-py : remove unused import
2024-05-25 11:11:48 +10:00
Georgi Gerganov
d041d2ceaa
flake.lock: Update (#7232)
Flake lock file updates:

• Updated input 'flake-parts':
    'github:hercules-ci/flake-parts/e5d10a24b66c3ea8f150e47dfdb0416ab7c3390e?narHash=sha256-yzcRNDoyVP7%2BSCNX0wmuDju1NUCt8Dz9%2BlyUXEI0dbI%3D' (2024-05-02)
  → 'github:hercules-ci/flake-parts/8dc45382d5206bd292f9c2768b8058a8fd8311d9?narHash=sha256-/GJvTdTpuDjNn84j82cU6bXztE0MSkdnTWClUCRub78%3D' (2024-05-16)
• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/63c3a29ca82437c87573e4c6919b09a24ea61b0f?narHash=sha256-4cPymbty65RvF1DWQfc%2BBc8B233A1BWxJnNULJKQ1EY%3D' (2024-05-02)
  → 'github:NixOS/nixpkgs/4a6b83b05df1a8bd7d99095ec4b4d271f2956b64?narHash=sha256-%2BNpbZRCRisUHKQJZF3CT%2Bxn14ZZQO%2BKjxIIanH3Pvn4%3D' (2024-05-17)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-24 08:59:06 -07:00
Brian
27891f6db0
docker.yml: disable light-intel and server-intel test (#7515)
* docker.yml: disable light-intel test

* docker.yml: disable server-intel test
2024-05-24 23:47:56 +10:00
fairydreaming
fbca2f27fc
Add support for ArcticForCausalLM (#7020)
* common : increase max number of experts to 128

* common : add tensor LLM_TENSOR_FFN_NORM_EXPS for normalization before MoE that runs in parallel to attention + ffn

* gguf-py : add architecture-specific block mappings that override selected general block mappings

* convert-hf : add model conversion support for ArcticForCausalLM

* convert-hf : use added_tokens_decoder from tokenizer_config.json to redefine tokens from SentencePiece model (only for ArcticForCausalLM)

* llama : add inference support for LLM_ARCH_ARCTIC

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2024-05-24 14:31:13 +02:00
Neo Zhang
0df0aa8e43
add build shared lib in win release package (#7438) 2024-05-24 10:06:56 +08:00
Georgi Gerganov
74f33adf5f
readme : remove trailing space (#7469) 2024-05-23 17:43:18 +03:00
Georgi Gerganov
1debe72737
ggml : silence UB sanitizer error during iq2_xxs quantization (#0) 2024-05-23 17:25:38 +03:00
Tristan Druyen
007489e895
Fix phi3 chat template confusion with zephyr (#7449)
* Fix phi3 template matching vs zephyr

* Add regression test for new phi3 chat template

* Implement review suggestions

* Fix phi3 jinja test templates & match by <|end|>

* Apply suggestion

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Add all phi3 template variants in tests

* Remove unneeded message trimming

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Fix tests to not expect trimmed messages

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-05-23 16:15:15 +02:00
Raj Hammeer Singh Hada
8b94e799df
readme : add Bunny in supported models [no ci] (#7469) 2024-05-23 15:30:13 +03:00
Daniel Bevenius
3015851c5a
llama : add getters for n_threads/n_threads_batch (#7464)
* llama : add getters for n_threads/n_threads_batch

This commit adds two new functions to the llama API. The functions
can be used to get the number of threads used for generating a single
token and the number of threads used for prompt and batch processing
(multiple tokens).

The motivation for this is that we want to be able to get the number of
threads that the a context is using. The main use case is for a
testing/verification that the number of threads is set correctly.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! llama : add getters for n_threads/n_threads_batch

Rename the getters to llama_n_threads and llama_n_threads_batch.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-05-23 15:29:26 +03:00
Georgi Gerganov
55ac3b7aea
ci : use Pythia models instead of OpenLlama (#7470)
* ci : start using Pythia models over OpenLlama

ggml-ci

* ci : disable q2_k ppl tests

* ci : use convert-hf-to-gguf.py

* ci : update gg_get_model

* ci : fix convert outfile name

ggml-ci

* llama : gptneox arch use F32 attn prec

ggml-ci
2024-05-23 15:28:14 +03:00
Victor Nogueira
dacfcebd60
readme : add GPT-NeoX + Pythia to the list of supported models (#7491) 2024-05-23 15:12:43 +03:00
fairydreaming
9b82476ee9
Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-NeoX base models) (#7461)
* convert-hf : add conversion of bloom-style qkv tensor to gpt-style qkv (code borrowed from BloomModel)

* llama : add inference support for LLM_ARCH_GPTNEOX

* llama : add model types for every Pythia variant and GPT-NeoX

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2024-05-23 11:49:53 +02:00
Georgi Gerganov
a61a94e543
llama : rename n_ctx -> cache.size, less confusing (#0) 2024-05-23 12:38:18 +03:00
Brian
152da28ae5
labeler.yml: add embedding label detector [no ci] (#7482) 2024-05-23 17:40:43 +10:00