This commit contains a suggestion for adding the missing embd_to_audio
function from tts.cpp to tts-outetts.py. This introduces a depencency
numpy which I was not sure if that is acceptable or not (only PyTorch
was mentioned in referened PR).
Also the README has been updated with instructions to run the example
with llama-server and the python script.
Refs: https://github.com/ggerganov/llama.cpp/pull/10784#issuecomment-2548377734
* cli : auto activate conversation mode if chat template is detected
* add warn on bad template
* update readme (writing with the help of chatgpt)
* update readme (2)
* do not activate -cnv for non-instruct models
* examples : add README.md to tts example [no ci]
* squash! examples : add README.md to tts example [no ci]
Fix heading to be consistent with other examples, and add a quickstart
section to README.md.
* squash! examples : add README.md to tts example [no ci]
Fix spelling mistake.
* server : add tooltips to settings and themes btn
This commit adds tooltips to the settings and themes buttons in the
webui. The tooltip will be displayed below the actual buttons when
hovered over.
The motivation for this change is to clarify the purpose of the themes
button.
* squash! server : add tooltips to settings and themes btn
This commit adds a tooltip to the '...' button when a chat has been
started. The tooltip is "Chat options" which think could be a good
description as the dropdown contains options to delete or download the
current chat.
* rm tooltip for 3 dots button
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
The main motivation for this change is it was not handing
ctrl-c/ctrl-d correctly. Modify `read_user_input` to handle EOF,
"/bye" command, and empty input cases. Introduce `get_user_input`
function to manage user input loop and handle different return
cases.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
* 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
* server/bench:
- support openAI streaming standard output with [DONE]\n\n
- export k6 raw results in csv
- fix too many tcp idle connection in tcp_wait
- add metric time to emit first token
* server/bench:
- fix when prometheus not started
- wait for server to be ready before starting bench
In common/common.cpp:
* Convert usage of stat() function call to check if file exists to standard library function std::filesystem::exists (error unable to match to correct function signature)
* Additional conditions to check if PATH_MAX is already defined in WIN32 environment (warning it is already defined in MSYS2)
In examples/run/run.cpp:
* Add io.h header inclusion (error cannot find function _get_osfhandle)
* Change initialisers for OVERLAPPED to empty struct (warning about uninitialised members)
* Add initialiser for hFile (warning it may be uninitialised)
* Add cast for curl_off_t percentage value to long int in generate_progress_prefix function (warning that curl_off_t is long long int)
In ggml/src/ggml-opencl/ggml-opencl.cpp:
* Initialise certain declared cl_mem variables to nullptr for greater safety (warning about B_d variable possibly used unassigned)
Warning types fixed (observed under MSYS2 GCC 14.2.0):
* format '%ld' expects argument of type 'long int', but argument has type 'size_t'
* llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:81:46: warning: missing initializer for member '_STARTUPINFOA::lpDesktop' [-Wmissing-field-initializers] (emitted for all struct field except first)
* more perfo with llamafile tinyblas on x86_64.
- add bf16 suport
- change dispache strategie (thanks:
https://github.com/ikawrakow/ik_llama.cpp/pull/71 )
- reduce memory bandwidth
simple tinyblas dispache and more cache freindly
* tinyblas dynamic dispaching
* sgemm: add M blocs.
* - git 2.47 use short id of len 9.
- show-progress is not part of GNU Wget2
* remove not stable test
This commit updates the `examples/run/README.md` file to include a new
option for setting the temperature and updates the `run.cpp` file to
parse this option.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
Set default width to whatever the terminal is. Also fixed a small bug around
default n_gpu_layers value.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
* server: avoid overwriting Authorization header
If no API key is set, leave the Authorization header as is. It may be
used by another part of the Web stack, such as an authenticating proxy.
Fixes https://github.com/ggerganov/llama.cpp/issues/10854
* rebuild
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* server : add "tokens" output
ggml-ci
* server : output embeddings for all tokens when pooling = none
ggml-ci
* server : update readme [no ci]
* server : fix spacing [no ci]
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* server : be explicit about the pooling type in the tests
ggml-ci
* server : update /embeddings and /v1/embeddings endpoints
ggml-ci
* server : do not normalize embeddings when there is no pooling
ggml-ci
* server : update readme
ggml-ci
* server : fixes
* tests : update server tests
ggml-ci
* server : update readme [no ci]
* server : remove rebase artifact
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* server : add "tokens" output
ggml-ci
* server : update readme
ggml-ci
* server : return tokens ids only if requested
ggml-ci
* tests : improve "tokens" type check
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* server : remove "tokens" from the OAI endpoint
ggml-ci
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* 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>
* Update server JSON response.
* Add unit test to check `has_new_line` JSON response
* Remove `has_new_line` unit test changes.
* Address code review comment: type check for `has_new_line` in unit test
* get rid of completion.js
* extract chat bubble to a component
* add tok/s info
* sync
* fix BASE_URL
* only extract timings when it's enabled
* fix auto scroll
* 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
* llama : use cmake for swift build
* swift : <> -> ""
* ci : remove make
* ci : disable ios build
* Revert "swift : <> -> """
This reverts commit d39ffd9556.
* ci : try fix ios build
* ci : cont
* ci : cont
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server : (refactor) no more json in server_task input
* add test for slots endpoint
* add tests for /props and /slots
* remove task inf_type
* fix CI by adding safe_json_to_str
* add "model_path" to /props
* update readme
* server : various fixes
ggml-ci
* server : show curent seed in slot_params
ggml-ci
* fix /slots endpoint
* Update examples/server/server.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server : reflect endpoint response changes in the readme
ggml-ci
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* 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>
* hide buttons in dropdown menu
* use npm as deps manager and vite as bundler
* fix build
* fix build (2)
* fix responsive on mobile
* fix more problems on mobile
* sync build
* (test) add CI step for verifying build
* fix ci
* force rebuild .hpp files
* cmake: clean up generated files pre build
* readme : document --no-display-prompt
* readme : update default prompt context size
* readme : remove unnecessary indentation
Indenting a line with four spaces makes Markdown treat that section as
plain text.
* readme : indent commands under bullets
* readme : indent commands in lettered list
* 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
* server : replace behave with pytest
* fix test on windows
* misc
* add more tests
* more tests
* styling
* log less, fix embd test
* added all sequential tests
* fix coding style
* fix save slot test
* add parallel completion test
* fix parallel test
* remove feature files
* update test docs
* no cache_prompt for some tests
* add test_cache_vs_nocache_prompt
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>
* llama : accept a list of devices to use to offload a model
* accept `--dev none` to completely disable offloading
* fix dev list with dl backends
* rename env parameter to LLAMA_ARG_DEVICE for consistency
* Add download chat feature to server chat
Add a download feature next to the delete chat feature in the server vue chat interface.
* code style
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Samplers sequence: simplified and input field.
* Removed unused function
* Modify and use `settings-modal-short-input`
* rename "name" --> "label"
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* server : (web ui) add copy btn for code blocks
* fix problem with api key
* use settings-modal-short-input component
* always show copy btn for code snippet
Converter script can now read these two fields as a detailed base model and dataset source.
This was done so that it will be easier for Hugging Face to integrate detailed metadata as needed.
- base_model_sources (List[dict], optional)
- dataset_sources (List[dict], optional)
Dataset now represented as:
- general.dataset.count
- general.dataset.{id}.name
- general.dataset.{id}.author
- general.dataset.{id}.version
- general.dataset.{id}.organization
- general.dataset.{id}.description
- general.dataset.{id}.url
- general.dataset.{id}.doi
- general.dataset.{id}.uuid
- general.dataset.{id}.repo_url
This also adds to base model these metadata:
- general.base_model.{id}.description
* Add back samplers to server
* Added tooltips with basic information
* Fixed stretching of input fields.
* use component for settings input, move help msg to tooltips
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* ggml : add ggml_flash_attn_ext_get_prec
* metal : use F16 precision in FA kernels
ggml-ci
* metal : minor clean-up
* metal : compile-guard bf16 FA kernels
ggml-ci
* build : remove obsolete compile flag [no ci]
* metal : prevent int overflows [no ci]
* cuda : disable BF16 FA
ggml-ci
* metal : fix BF16 requirement for FA kernels
ggml-ci
* make : clean-up [no ci]
* server : simple chat UI with vuejs and daisyui
* move old files to legacy folder
* embed deps into binary
* basic markdown support
* add conversation history, save to localStorage
* fix bg-base classes
* save theme preferences
* fix tests
* regenerate, edit, copy buttons
* small fixes
* docs: how to use legacy ui
* better error handling
* make CORS preflight more explicit
* add GET method for CORS
* fix tests
* clean up a bit
* better auto scroll
* small fixes
* use collapse-arrow
* fix closeAndSaveConfigDialog
* small fix
* remove console.log
* fix style for <pre> element
* lighter bubble color (less distract when reading)
* llama: Refactor string_split to use template specialization, fixes parsing strings with spaces
* llama: Add static_assert in the string_split template to ensure the correct template specialization is used for std::string
* added classic vim support
* fixed ring update, removed blank line
* minor
* minor
* minor doc update
* removed uneeded var
* minor
* minor
* fixed job_start creating new scratch buffers
* fixed job_start creating new scratch buffers
* fixed ghost text indenting when expandtab is on
* removed unused code
* minor
* unified fim_on_exit
* minor
* vim ghost text rendering now uses pos_x and pos_y parameters
* renamed *_hlgroup to hlgroup_*
* renamed *_ghost_text to ghost_text_*, moved nvim/vim detection to llama#init()
* minor
---------
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
* llama : deprecate softmax sampler + fix dist sampler
ggml-ci
* tests : replace macros with functions
ggml-ci
* sampling : change temperature sampler logic
For t <= 0.0f, keep the max logit intact and set the rest to -inf
* cont : no need for special "greedy" logic
top-k == 1 is the same
* tests : init prob correctly
* llama : handle temp <= 0.0 in the temp_ext sampler too
ggml-ci
* cont : avoid extra loop in temperature sampler for sub-zero temp
ggml-ci
Prior to this commit, using a JSON Schema containing a string
with `pattern` regular expression that uses top-level alternation
(e.g. `"pattern": "^A|B|C|D$"`) would result in invalid JSON
output from the constrained sampling grammar, because it
ended up creating a grammar rule like this for the string:
```
thing ::= "\"" "A" | "B" | "C" | "D" "\"" space
```
Note that this rule will only match a starting quote for the "A" case,
and will only match an ending quote for the "D" case,
so this rule will always produce invalid JSON when used for sampling
(that is, the JSON will always be lacking the starting quote,
the ending quote, or both).
This was fixed in a simple way by adding parentheses to the
generated rule (for all string pattern rules, to keep it simple),
such that the new generated rule looks like this (correct):
```
thing ::= "\"" ("A" | "B" | "C" | "D") "\"" space
```
* Initial XTC commit
Adds XTC sampler, not activated by default, but recommended settings by default.
* Cleanup
* Simplified chances calculation
To be more inline with the original implementation, chance is calculated once at the beginning.
* First fixes by comments
Still need to look into sorting
* Fixed trailing backspaces
* Fixed RNG to be reproduceable
Thanks to @slaren for directions
* Fixed forgotten header
* Moved `min_keep`
Moved from conditions to a simple check at the end.
* Fixed broken randomization
Thanks to @slaren for explanation
* Swapped sorting for a custom algorithm
Shifts tokens to remove the penalized ones, then puts the penalized at the back. Should make `min_keep` still viable.
* Algorithm rework
1. Scan token from top till the first non-penalizable
2. Remove the last captured token (the least probable above threshold)
3. Shift all tokens to override the remaining penalizable
4. Penalize and put them at the the bottom.
* Added XTC to `test-sampling`
* Simplified algorithm and more tests
* Updated info in common and args
* Merged back lost commits in common and arg
* Update dump info in common
* Fixed incorrect min_keep check
* Added XTC to README
* Renamed parameters, fixed info and defaults
* probability is at 0 by default, but XTC is included in sampling queue
* threshold higher than 0.5 switches XTC off
* Initial server support
* Added XTC to server UIs
* Fixed labels in old server UI
* Made algorithm safer and more readable
* Removed xtc_threshold_max
* Fixed arg after update
* Quick fixes by comments
* Simplified algorithm since threshold_max is removed
* Renamed random distribution
* Fixed tests and outdated README
* Small fixes
* server : accept extra_context for the infill endpoint
ggml-ci
* server : update readme [no ci]
* server : use repo-level FIM pattern if possible
ggml-ci
* llama : improve infill support
ggml-ci
* llama : add more FIM token strings
ggml-ci
* server : update prompt on slot restore (#9800)
* gguf : deprecate old FIM token KVs
* ggml : do not use BLAS with types without to_float
* ggml : return pointer from ggml_internal_get_type_traits to avoid unnecessary copies
* ggml : rename ggml_internal_get_type_traits -> ggml_get_type_traits
it's not really internal if everybody uses it
* rerank : use [SEP] token instead of [BOS]
ggml-ci
* common : sanity check for non-NULL tokens
ggml-ci
* ci : adjust rank score interval
ggml-ci
* ci : add shebang to run.sh
ggml-ci
* make sure params --split and --merge are not specified at same time
* update gguf-split params parse logic
* Update examples/gguf-split/gguf-split.cpp
Co-authored-by: slaren <slarengh@gmail.com>
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
* server : add --no-context-shift option
* small fix
* Update examples/server/tests/features/embeddings.feature
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* tests : minor fix
* revert usage of GGML_ASSERT
* update server documentation
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* added cli arg to disable context shift
* reverted precommit
* updated README.md for main
* white space
* allow disabling context shift in the server
* Update common/arg.cpp
no-context-shift only works for main example
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* added server example to --no-context-shift args
* removed server changes
* white space
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Adding loading page for '/' server requests
* set content when model is loading
* removed loading html file
* updated cmakelist
* updated makefile
* cleaned up whitespace
* cleanup for PR removed error
* updated server test to handle 503 HTML
* updated server test to handle 503 HTML
* ca†ch 503 before parsing json
* revert test
* account for both api and web browser requests
* precommit corrections
* eol fix
* revert changes to pre-commit
* removed print statement
* made loading message more descriptive
* also support .html files
---------
Co-authored-by: VJHack <flymyplane21@gmail.com>
Co-authored-by: Vinesh Janarthanan <36610342+VJHack@users.noreply.github.com>
* llama : llama_perf + option to disable timings during decode
ggml-ci
* common : add llama_arg
* Update src/llama.cpp
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* perf : separate functions in the API
ggml-ci
* perf : safer pointer handling + naming update
ggml-ci
* minor : better local var name
* perf : abort on invalid sampler pointer
ggml-ci
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* server : added with_pieces functionality to /tokenize endpoint
* server : Add tokenize with pieces tests to server.feature
* Handle case if tokenizer splits along utf8 continuation bytes
* Add example of token splitting
* Remove trailing ws
* Fix trailing ws
* Maybe fix ci
* maybe this fix windows ci?
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Arm AArch64: Documentation updates
* Update docs/build.md to include information on how to enable the Arm optimized gemm/gemv kernels
* Update examples/quantize/README.md with information on the Q4_0_4_4, Q4_0_4_8 and Q4_0_8_8 formats
* Add newline to the end of docs/build.md
* common : do not add null tokens during warmup
ggml-ci
* llama : check that the input tokens are valid
ggml-ci
* tests : fix batch size of bert model
ggml-ci
- Add `struct llama_sampler` and `struct llama_sampler_i`
- Add `llama_sampler_` API
- Add `llama_sampler_chain_` API for chaining multiple samplers
- Remove `LLAMA_API_INTERNAL`
- Add `llama_perf_` API and remove old `llama_print_timings` and `llama_reset_timings`
* ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b
* ggml-quants : faster 1.625 bpw AVX2 vec_dot
Not using a lookup table anymore makes it match q4_0 speed.
* gguf-py : fix formatting
* llama : remove spaces on empty line
* ggml-quants : subtract 1 when back in epi8
This makes the 1.625 bpw type go faster than q4_0. Still not the fastest.
* ggml-quants : Q2_2 now faster than Q4_K on with AVX2
* ggml-quants : cleanup Q1_3 code formatting
* ggml-quants : ARM NEON vec_dot for q2_2 and q1_3
* ggml-quants : use ceiling division when quantizing q1_3
* convert-hf : simplify BitNet pre-quantization
This still results in the exact same tensor weights and scales,
but it reveals some weirdness in the current algorithm.
* convert-hf : allow converting the weird BitNet 1.3B
Its FFN size is 5460 which is not convenient.
The offending tensors are kept in F16,
which makes the final model 5.01 bpw.
* bitnet : replace 1.58b with b1.58, as in the paper
* ggml-quants : fix build failure on Windows
* ggml-quants : attempt to fix Arm 32-bit support
* ggml : add some informative comments in q1_3 vec_dot
* ggml : add TQ1_0 and TQ2_0 ternary quantization types
* ggml : even faster TQ2_0
* ggml : also faster TQ1_0
Same optimization as for TQ2_0 by offsetting the sum instead of the weights.
This makes TQ1_0 almost as fast as Q8_0 on AVX2.
* ggml : fix build issues in certain environments
* ggml : add NEON vec_dot implementation for TQ1_0 and TQ2_0
* ggml : avoid directly using vmlal_high_s8, for 32-bit ARM compat
The compiler seems smart enough to use the same instruction
even when using vget_high_s8 instead.
* ggml : remove q1_3 and q2_2
No more 1.625 bpw and 2.000 bpw,
now instead using 1.6875 bpw and 2.0625 bpw
with TQ1_0 and TQ2_0, respectively.
* llama : remove the separate scale tensors of BitNet b1.58
They won't be needed, since the remaining ternary quant types have
built-in scales.
* ggml-quants : rename fields of TQ1_0 and TQ2_0 structs for consistency
* ggml-quants : allow using vdotq_s32 in TQ2_0 vec_dot
Not yet tested on hardware which supports it,
might not work or might not even compile. But also it might.
It should make the performance better on recent ARM CPUs.
* ggml-quants : remove comment about possible format change of TQ2_0
Making it slightly more convenient for AVX512
but less convenient for everything else is not worth the trouble.
* gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0
* ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0
This does not change anything for ternary models,
since their values should never end up being in halfway cases anyway.
* convert : allow direct conversion to TQ1_0 and TQ2_0
The token embeddings and output tensors are kept in F16
to allow quantizing them to Q4_K and Q6_K with llama-quantize.
* llama : handle fallback for TQ1_0 and TQ2_0 with Q4_0
Q4_0 is not completely symmetric (so not lossless for ternary models),
but it should be good enough.
* ggml-quants : allow using ARM dot product instructions for TQ1_0
* ggml-quants : deduplicate TQ1_0 and TQ2_0 __ARM_FEATURE_DOTPROD support
* ggml : remove unused ggml_mul special case
It would otherwise conflict with the more general
optimization coming with Mamba-2.
* ggml : handle TQ1_0 and TQ2_0 in dequantization-based operators
* test-backend-ops : add TQ1_0 and TQ2_0 comments for later
Not yet adding uncommented, because some backends like SYCL and Metal
do not properly handle unknown types in supports_op for GGML_OP_MUL_MAT.
(and Metal also doesn't handle it with GGML_OP_GET_ROWS)
Support for TQ1_0 and TQ2_0 for other backends than CPU
will be added in follow-up pull requests.
* server : remove multitask from server_task
* refactor completions handler
* fix embeddings
* use res_ok everywhere
* small change for handle_slots_action
* use unordered_set everywhere
* (try) fix test
* no more "mutable" lambda
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* use deque
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Introduce ggml_compute_threadpool
- OpenMP functional: check
- Vanilla ggml functional: Check
- ggml w/threadpool functional: Check
- OpenMP no regression: No glaring problems
- Vanilla ggml no regression: No glaring problems
- ggml w/threadpool no regression: No glaring problems
* Minor fixes
* fixed use after release bug
* fixed a harmless race condition
* Fix Android bulid issue
* fix more race conditions
* fix deadlock for cases where cgraph.n_nodes == 1
and fix --poll case
* threadpool: use cpu_get_num_math to set the default number of threadpool threads
This way we avoid using E-Cores and Hyperthreaded siblings.
* bench: create fresh threadpool for each test
For benchmarking it's better to start a fresh pool for each test with the exact number of threads
needed for that test. Having larger pools is suboptimal (causes more load, etc).
* atomics: always use stdatomics with clang and use relaxed memory order when polling in ggml_barrier
This also removes sched_yield() calls from ggml_barrier() to match OpenMP behavior.
* threadpool: make polling the default to match openmp behavior
All command line args now allow for setting poll to 0 (false).
* threadpool: do not wakeup threads in already paused threadpool
* fix potential race condition in check_for_work
* threadpool: do not create two threadpools if their params are identical
* threadpool: reduce pause/resume/wakeup overhead in common cases
We now start threadpool in paused state only if we have two.
The resume is now implicit (ie new work) which allows for reduced locking and context-switch overhead.
* threadpool: add support for hybrid polling
poll params (--poll, ...) now specify "polling level", i.e. how aggresively we poll before waiting on cond.var.
poll=0 means no polling, 1 means poll for 128K rounds then wait, 2 for 256K rounds, ...
The default value of 50 (ie 50x128K rounds) seems like a decent default across modern platforms.
We can tune this further as things evolve.
* threadpool: reduce the number of barrier required
New work is now indicated with an atomic counter that is incremented for
each new graph that needs to be computed.
This removes the need for extra barrier for clearing the "new_work" and
removes the special case for trivial graphs.
* threadpool: remove special-casing for disposable threadpools
With the efficient hybrid polling there is no need to make disposable pools any different.
This simplifies the overall logic and reduces branching.
Include n_threads in debug print for disposable threadpool.
Declare pause and stop flags as atomic_bool
This doesn't actually generate any memory barriers and simply informs
the thread sanitizer that these flags can be written & read by different
threads without locking.
* threadpool: do not clear barrier counters between graphs computes (fixes race with small graphs)
This fixes the race condition with very small graphs where the main thread happens to
start a new graph while the workers are just about to exit from barriers.
* threadpool: use relaxed order for chunk sync
Full memory barrier is an overkill for this since each thread works on different chunk
* threadpool: remove abort_callback from threadpool state
* threadpool: better naming for thread/cpumask releated functions
* threadpool: consistent use of int type for n_threads params
* threadpool: add support for ggml_threadpool_params_default/init
Also removes the need for explicit mask_specified param.
all-zero cpumask means use default (usually inherited) cpu affinity mask.
* threadpool: move typedef into ggml.h
* threadpool: fix apply_priority() function name
* threadpool: fix swift wrapper errors due to n_threads int type cleanup
* threadpool: enable --cpu-mask and other threadpool related options only if threadpool is enabled
* threadpool: replace checks for compute_thread ret code with proper status check
* threadpool: simplify threadpool init logic and fix main thread affinity application
Most of the init code is now exactly the same between threadpool and openmp.
* threadpool: update threadpool resume/pause function names
* threadpool: enable openmp by default for now
* threadpool: don't forget to free workers state when omp is enabled
* threadpool: avoid updating process priority on the platforms that do not require it
On Windows we need to change overall process priority class in order to set thread priorities,
but on Linux, Mac, etc we do not need to touch the overall process settings.
* threadpool: update calling thread prio and affinity only at start/resume
This avoids extra syscalls for each graph_compute()
* llama-bench: turn threadpool params into vectors, add output headers, etc
* llama-bench: add support for cool off between tests --delay
This helps for long running tests on platforms that are thermally limited (phones, laptops, etc).
--delay (disabled by default) introduces the sleep for N seconds before starting each test.
* threadpool: move process priority setting into the apps (bench and cli)
This avoids changing the overall process priority on Windows for the apps
that use ggml/llama.cpp directy.
* threadpool: move all pause/resume logic into ggml
* threadpool: futher api cleanup and prep for future refactoring
All threadpool related functions and structs use ggml_threadpool prefix.
* threadpool: minor indent fixes
* threadpool: improve setprioty error message
* Update examples/llama-bench/llama-bench.cpp
Co-authored-by: slaren <slarengh@gmail.com>
* threadpool: fix indent in set_threadpool call
* use int32_t for n_thread type in public llama.cpp API
* threadpool: use _new and _free instead of _create and _release
* fix two more public APIs to use int32_t for n_threads
* build: set _GNU_SOURCE for Adroid
---------
Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>
Co-authored-by: fmz <quic_fzaghlou@quic.com>
Co-authored-by: Max Krasnyansky <max.krasnyansky@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
This change fixes a bug where replacing text in a very long string could
cause llama.cpp to hang indefinitely. This is because the algorithm used
was quadratic, due to memmove() when s.replace() is called in a loop. It
seems most search results and LLM responses actually provide the O(n**2)
algorithm, which is a great tragedy. Using a builder string fixes things
* llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model.
- The CLIP model now prioritizes the Vulkan backend over the CPU when vulkan available.
- A GGML_OP_ACC shader has been added.
- The encoding performance of the CLIP model improved from 4.2s on the CPU to 0.9s on the GPU.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* fix-up coding style.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* Fix-up the missing initial parameter to resolve the compilation warning.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* [fix] Add missing parameters.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* [fix] Use nb1 and nb2 for dst.
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
* Fix check results ggml_acc call
---------
Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>
Co-authored-by: 0cc4m <picard12@live.de>
* server : refactor middleware and /health endpoint
* move "fail_on_no_slot" to /slots
* Update examples/server/server.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* fix server tests
* fix CI
* update server docs
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* gguf-py : add T5ENCODER model architecture
* common : call llama_decode() during warmup only if the model has decoder
* convert-hf : add T5EncoderModel
* llama : add llama_model_has_decoder() API function
* llama : split build_t5() into build_t5_encoder() and build_t5_decoder()
* llama : add support for LLM_ARCH_T5ENCODER
* llama-embedding : add support for LLAMA_POOLING_TYPE_NONE
* llama-embedding : add support for encoder-only models
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit adds the `--pooling` option to the README.md file in the
`examples/embedding` directory.
The motivation for adding this options is that currently if the model
used does not specify a pooling type the embedding example will fail
with the following error message:
```console
main: error: pooling type NONE not supported
```
This commit also updates the name of the executable in the examples
section.
* common : Changed tuple to struct (TODO fix)
Use struct `llama_init_result` to replace the previous
std::tuple<struct llama_model *, struct llama_context *>
* delete llama_init_default_params()
* delete the extra whitespace
* [example] batched-bench "segmentation fault"
When `llama-batched-bench` is invoked _without_ setting `-npl`, "number
of parallel prompts", it segfaults.
The segfault is caused by invoking `max_element()` on a zero-length
vector, `n_pl`
This commit addresses that by first checking to see if the number of
parallel prompts is zero, and if so sets the maximum sequence size to 1;
otherwise, sets it to the original, the result of `max_element()`.
Fixes, when running `lldb build/bin/llama-batched-bench -- -m models/Meta-Llama-3-8B.gguf`
```
* thread #1, queue = 'com.apple.main-thread', stop reason = EXC_BAD_ACCESS (code=1, address=0x0)
frame #0: 0x000000010000366c llama-batched-bench`main(argc=3, argv=0x000000016fdff268) at batched-bench.cpp:72:28
69 llama_context_params ctx_params = llama_context_params_from_gpt_params(params);
70
71 // ensure enough sequences are available
-> 72 ctx_params.n_seq_max = *std::max_element(n_pl.begin(), n_pl.end());
```
* Update examples/batched-bench/batched-bench.cpp
Co-authored-by: compilade <git@compilade.net>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: compilade <git@compilade.net>
* llama : refactor session file management
* llama : saving and restoring state checks for overflow
The size of the buffers should now be given to the functions working
with them, otherwise a truncated file could cause out of bound reads.
* llama : stream from session file instead of copying into a big buffer
Loading session files should no longer cause a memory usage spike.
* llama : llama_state_get_size returns the actual size instead of max
This is a breaking change, but makes that function *much* easier
to keep up to date, and it also makes it reflect the behavior
of llama_state_seq_get_size.
* llama : share code between whole and seq_id-specific state saving
Both session file types now use a more similar format.
* llama : no longer store all hparams in session files
Instead, the model arch name is stored.
The layer count and the embedding dimensions of the KV cache
are still verified when loading.
Storing all the hparams is not necessary.
* llama : fix uint64_t format type
* llama : various integer type cast and format string fixes
Some platforms use "%lu" and others "%llu" for uint64_t.
Not sure how to handle that, so casting to size_t when displaying errors.
* llama : remove _context suffix for llama_data_context
* llama : fix session file loading
llama_state_get_size cannot be used to get the max size anymore.
* llama : more graceful error handling of invalid session files
* llama : remove LLAMA_MAX_RNG_STATE
It's no longer necessary to limit the size of the RNG state,
because the max size of session files is not estimated anymore.
* llama : cast seq_id in comparison with unsigned n_seq_max
Changes:
- Move each example into its own function. This makes the code much
easier to read and understand.
- Make the program easy to only run one test by commenting out function
calls in main().
- Make the output easy to parse by indenting the output for each example.
- Add shebang and +x bit to make it clear it's an executable.
- Make the host configurable via --host with a default 127.0.0.1:8080.
- Make the code look in the tools list to call the registered tool,
instead of hardcoding the returned values. This makes the code more
copy-pastable.
- Add error checking, so that the program exits 1 if the LLM didn't
returned expected values. It's super useful to check for correctness.
Testing:
- Tested with Mistral-7B-Instruct-v0.3 in F16 and Q5_K_M and
Meta-Llama-3-8B-Instruct in F16 and Q5_K_M.
- I did not observe a failure even once in Mistral-7B-Instruct-v0.3.
- Llama-3 failed about a third of the time in example_concurrent: it
only returned one call instead of 3. Even for F16.
Potential follow ups:
- Do not fix the prompt encoding yet. Surprisingly it mostly works even
if the prompt encoding is not model optimized.
- Add chained answer and response.
Test only change.
* fix continuing generating blank lines after getting EOT token or EOS token from LLM
* change variable name to is_done (variable name suggested by ggerganov)
* minor : fix trailing whitespace
* minor : add space
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Main thing is that the default output filename will take this form
{name}{parameters}{finetune}{version}{encoding}{kind}
In addition this add and remove some entries in the KV store and adds a metadata class with automatic heuristics capability to derive some values based on model card content
* No Change:
- Internal GGUF Spec
- `general.architecture`
- `general.quantization_version`
- `general.alignment`
- `general.file_type`
- General Model Details
- `general.name`
- `general.author`
- `general.version`
- `general.description`
- Licensing details
- `general.license`
- Typically represents the converted GGUF repo (Unless made from scratch)
- `general.url`
- Model Source during conversion
- `general.source.url`
* Removed:
- Model Source during conversion
- `general.source.huggingface.repository`
* Added:
- General Model Details
- `general.organization`
- `general.finetune`
- `general.basename`
- `general.quantized_by`
- `general.size_label`
- Licensing details
- `general.license.name`
- `general.license.link`
- Typically represents the converted GGUF repo (Unless made from scratch)
- `general.doi`
- `general.uuid`
- `general.repo_url`
- Model Source during conversion
- `general.source.doi`
- `general.source.uuid`
- `general.source.repo_url`
- Base Model Source
- `general.base_model.count`
- `general.base_model.{id}.name`
- `general.base_model.{id}.author`
- `general.base_model.{id}.version`
- `general.base_model.{id}.organization`
- `general.base_model.{id}.url` (Model Website/Paper)
- `general.base_model.{id}.doi`
- `general.base_model.{id}.uuid`
- `general.base_model.{id}.repo_url` (Model Source Repository (git/svn/etc...))
- Array based KV stores
- `general.tags`
- `general.languages`
- `general.datasets`
---------
Co-authored-by: compilade <git@compilade.net>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* [CANN] Add Ascend NPU backend
Ascend is a full-stack AI computing infrastructure for industry
applications and services based on Huawei Ascend processors and
software.
CANN (Compute Architecture of Neural Networks), developped by
Huawei, is a heterogeneous computing architecture for AI.
Co-authored-by: wangshuai09 <391746016@qq.com>
* delete trailing whitespaces
* Modify the code based on review comment
* Rename LLAMA_CANN to GGML_CANN
* Make ggml-common.h private
* add ggml_cann prefix for acl funcs
* Add logging for CANN backend
* Delete Trailing whitespace
---------
Co-authored-by: wangshuai09 <391746016@qq.com>
* Update clib.json to point to Cyan4973 original xxhash
Convinced Cyan4973 to add clib.json directly to his repo, so can now point the clib package directly to him now. Previously pointed to my fork with the clib.json package metadata
https://github.com/Cyan4973/xxHash/pull/954
* gguf-hash: readme update to point to Cyan4973 xxHash repo [no ci]
The --help option on export-lora isn't accepted as valid. The help still gets displayed by default, but the script exits with an error message and nonzero status.
The README.md had a stale information. In particular, the --ctx-size
"defaults to 512" confused me and I had to check the code to confirm
this was false. This the server is evolving rapidly, it's probably
better to keep the source of truth at a single place (in the source) and
generate the README.md based on that.
Did:
make llama-server
./llama-server --help > t.txt
vimdiff t.txt examples/server/README.md
I copied the content inside a backquote block. I would have preferred
proper text but it would require a fair amount of surgery to make the
current output compatible with markdown. A follow up could be to
automate this process with a script.
No functional change.
* server : handle content array in chat API
* Update examples/server/utils.hpp
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Radoslav Gerganov
Georgi Gerganov
Daniel Bevenius
ebraminio
Xuan Son Nguyen
Eric Curtin
Johannes Gäßler
Pierrick Hymbert
Peter
ag2s20150909
Isaac McFadyen
Alexey Parfenov
Reza Kakhki
Djip007
NeverLucky
Diego Devesa
Gaetan Bisson
krystiancha
Bartowski
Vinesh Janarthanan
Michelle Tan
HimariO
cduk
CentricStorm
qingy1337
kallewoof
Yüg
Plamen Minev
aryantandon01
piDack
Nikolaos Pothitos
haopeng
alek3y
Robert Collins
Ting Lou
Random Fly
brucepro
MaggotHATE
Jhen-Jie Hong
Brian
sasha0552
Kevin Gibbons
Rich Dougherty
wwoodsTM
Michael Podvitskiy
Michael Coppola
Ouadie EL FAROUKI
Joe Eli McIlvain
VoidIsVoid
Daniel Kleine
Zhenwei Jin
compilade
vb
StrangeBytesDev
Sigbjørn Skjæret
Eric Zhang
Neo Zhang Jianyu
Bert Wagner
Mathijs Henquet
fengerhu1
Antonis Makropoulos
Dan Johansson
Aarni Koskela
Guoliang Hua
tc-mb
Faisal Zaghloul
Jan Boon
Xie Yanbo
Justine Tunney
João Dinis Ferreira
fairydreaming
Changyeon Kim
Aisuko
gtygo
Riceball LEE
Jiří Podivín
Mathieu Geli
Neo Zhang
Liu Jia
ardfork
Brian Cunnie
Igor Okulist
Yaiko
Ujjawal Panchal
Vali Malinoiu
devojony
M-A
Huifeng Ou
RunningLeon
hipudding
Masaya, Kato
Steve Bonds
Douglas Hanley