vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
6564 commits 3 branches 196 tags 386 MiB
Commit graph

341 commits

Author SHA1 Message Date
Concedo
f9f1585a7f broken merge - kcpp changes will be applied above this commit for better tracking. 2025-01-03 23:49:17 +08:00
Molly Sophia
4b0c638b9a
common : disable KV cache shifting automatically for unsupported models (#11053) 
* Disable KV cache shifting automatically for unsupported models

instead of exiting directly

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update common/common.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-01-03 14:13:18 +02:00
Georgi Gerganov
f66f582927
llama : refactor src/llama.cpp (#10902) 
* llama : scatter llama.cpp into multiple modules (wip)

* llama : control-vector -> adapter

* llama : arch

* llama : mmap

ggml-ci

* ci : remove BUILD_SHARED_LIBS=OFF

ggml-ci

* llama : arch (cont)

ggml-ci

* llama : chat

ggml-ci

* llama : model

ggml-ci

* llama : hparams

ggml-ci

* llama : adapter

ggml-ci

* examples : fix

ggml-ci

* rebase

ggml-ci

* minor

* llama : kv cache

ggml-ci

* llama : impl

ggml-ci

* llama : batch

ggml-ci

* cont

ggml-ci

* llama : context

ggml-ci

* minor

* llama : context (cont)

ggml-ci

* llama : model loader

ggml-ci

* common : update lora

ggml-ci

* llama : quant

ggml-ci

* llama : quant (cont)

ggml-ci

* minor [no ci]
 2025-01-03 10:18:53 +02:00
Concedo
911da8765f Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	examples/llama.android/llama/src/main/cpp/llama-android.cpp
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/server/bench/README.md
#	examples/server/tests/README.md
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	tests/test-backend-ops.cpp
 2025-01-03 11:56:20 +08:00
Xuan Son Nguyen
45095a61bf
server : clean up built-in template detection (#11026) 
* server : clean up built-in template detection

* fix compilation

* add chat template test

* fix condition
 2024-12-31 15:22:01 +01:00
Peter
6e1531aca5
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON (#11013) 
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)
 2024-12-31 01:46:06 +01:00
Concedo
ee486bad3e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
#	examples/CMakeLists.txt
#	examples/batched/batched.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/build.gradle.kts
#	examples/main/README.md
#	examples/retrieval/retrieval.cpp
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml.c
#	scripts/compare-commits.sh
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-sampling.cpp
 2024-12-19 11:57:43 +08:00
Georgi Gerganov
0bf2d10c55
tts : add OuteTTS support (#10784) 
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : be explicit about the pooling type in the tests

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* llama : add OuteTTS support (wip)

* wip

* extract features

* first conv

* group norm

* resnet conv

* resnet

* attn

* pos net

* layer norm

* convnext

* head

* hann window

* fix n_embd + remove llama.cpp hacks

* compute hann window

* fft

* spectrum processing

* clean-up

* tts : receive input text and generate codes

* clip : fix new conv name

* tts : minor fix

* tts : add header + minor fixes

ggml-ci

* tts : add matchematical constant

ggml-ci

* tts : fix sampling + cut initial noise

* tts : fixes

* tts : update default samplers

ggml-ci

* tts : text pre-processing

* tts : outetts-voc -> wavtokenizer-dec

* tts : remove hardcoded constants

ggml-ci

* tts : fix tensor shapes

* llama : refactor wavtokenizer tensors

ggml-ci

* cont

ggml-ci

* cont [no ci]

* llama : update WavTokenizer to non-causal attn

* llama : handle no-vocab detokenization

* tts : add Python example for OuteTTS (wip)

* tts : extend python example to generate spectrogram

ggml-ci

* server : fix rebase artifacts

* tts : enable "return_tokens" in Python example

ggml-ci

* tts : minor fixes

* common : support HF download for vocoder
 2024-12-18 19:27:21 +02:00
Georgi Gerganov
152610eda9
server : output embeddings for all tokens when pooling = none (#10861) 
* 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>
 2024-12-18 13:01:41 +02:00
Georgi Gerganov
644fd71b44
sampling : refactor + optimize penalties sampler (#10803) 
* sampling : refactor + optimize penalties sampler

ggml-ci

* common : apply ignore_eos as logit bias

ggml-ci

* batched : remove penalties sampler

* params : allow penalty_last_n == -1 to be equal to context size

ggml-ci

* common : by default, move the penalties at the end of the sampling chain

ggml-ci

* common : ignore all EOG tokens

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* common : move back the penalties at the front of the sampling chain

ggml-ci

* readme : restore hint about --ignore-eos flag [no ci]

* llama : minor

ggml-ci

* webui : update

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2024-12-16 12:31:14 +02:00
Concedo
f456ed7237 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/nix/package.nix
#	.devops/tools.sh
#	.github/workflows/build.yml
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	common/common.h
#	examples/llava/CMakeLists.txt
#	examples/run/CMakeLists.txt
#	examples/run/README.md
#	examples/run/run.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-kompute/ggml-kompute.cpp
#	tests/test-backend-ops.cpp
#	tests/test-rope.cpp
 2024-12-15 15:30:10 +08:00
Eric Curtin
c27ac678dd
Opt class for positional argument handling (#10508) 
Added support for positional arguments `model` and `prompt`. Added
functionality to download via strings like:

  llama-run llama3
  llama-run ollama://granite-code
  llama-run ollama://granite-code:8b
  llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
  llama-run huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
  llama-run https://example.com/some-file1.gguf
  llama-run some-file2.gguf
  llama-run file://some-file3.gguf

Signed-off-by: Eric Curtin <ecurtin@redhat.com>
 2024-12-13 19:34:25 +01:00
Concedo
ed75f8a741 up to date merge, without vulkan-gen-shaders. They will be built before each release from now on, as they are very large 2024-12-13 17:18:01 +08:00
Xuan Son Nguyen
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806) 
* common : improve ctv ctk cli argument

* regenerate docs

* even better approach

* use std::vector
 2024-12-12 22:53:05 +01:00
Concedo
557bcaf86e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.clang-tidy
#	.github/workflows/build.yml
#	Makefile
#	Package.swift
#	common/CMakeLists.txt
#	examples/batched-bench/CMakeLists.txt
#	examples/batched/CMakeLists.txt
#	examples/convert-llama2c-to-ggml/CMakeLists.txt
#	examples/cvector-generator/CMakeLists.txt
#	examples/embedding/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/export-lora/CMakeLists.txt
#	examples/gbnf-validator/CMakeLists.txt
#	examples/gguf-split/CMakeLists.txt
#	examples/gguf/CMakeLists.txt
#	examples/gritlm/CMakeLists.txt
#	examples/imatrix/CMakeLists.txt
#	examples/infill/CMakeLists.txt
#	examples/llama-bench/CMakeLists.txt
#	examples/llava/CMakeLists.txt
#	examples/lookahead/CMakeLists.txt
#	examples/lookup/CMakeLists.txt
#	examples/main-cmake-pkg/CMakeLists.txt
#	examples/main/CMakeLists.txt
#	examples/parallel/CMakeLists.txt
#	examples/passkey/CMakeLists.txt
#	examples/perplexity/CMakeLists.txt
#	examples/quantize-stats/CMakeLists.txt
#	examples/quantize/CMakeLists.txt
#	examples/retrieval/CMakeLists.txt
#	examples/run/CMakeLists.txt
#	examples/save-load-state/CMakeLists.txt
#	examples/server/CMakeLists.txt
#	examples/simple-chat/CMakeLists.txt
#	examples/simple/CMakeLists.txt
#	examples/speculative-simple/CMakeLists.txt
#	examples/speculative/CMakeLists.txt
#	examples/tokenize/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	pocs/vdot/CMakeLists.txt
#	src/CMakeLists.txt
#	src/unicode.cpp
#	tests/test-sampling.cpp
 2024-11-30 12:24:51 +08:00
Concedo
ec95241e38 temp checkpoint 2024-11-30 11:59:27 +08:00
Diego Devesa
7cc2d2c889
ggml : move AMX to the CPU backend (#10570) 
* ggml : move AMX to the CPU backend

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-11-29 21:54:58 +01:00
Xuan Son Nguyen
9f912511bc
common : fix duplicated file name with hf_repo and hf_file (#10550) 2024-11-27 22:30:52 +01:00
Concedo
ec581b19d8 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	examples/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/llama-bench/llama-bench.cpp
#	examples/server/README.md
#	examples/server/server.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/simple/simple.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-amx/CMakeLists.txt
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-kompute/CMakeLists.txt
#	ggml/src/ggml-kompute/ggml-kompute.cpp
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	pocs/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
 2024-11-26 17:01:20 +08:00
Diego Devesa
10bce0450f
llama : accept a list of devices to use to offload a model (#10497) 
* 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
 2024-11-25 19:30:06 +01:00
Diego Devesa
5931c1f233
ggml : add support for dynamic loading of backends (#10469) 
* ggml : add support for dynamic loading of backends

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-11-25 15:13:39 +01:00
Concedo
83350ec314 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/ISSUE_TEMPLATE/020-enhancement.yml
#	.github/ISSUE_TEMPLATE/030-research.yml
#	.github/ISSUE_TEMPLATE/040-refactor.yml
#	.github/workflows/build.yml
#	Makefile
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	examples/infill/infill.cpp
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup-stats.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/kernels/CMakeLists.txt
#	ggml/src/ggml-cann/kernels/dup.cpp
#	ggml/src/ggml-cann/kernels/get_row_f16.cpp
#	ggml/src/ggml-cann/kernels/get_row_f32.cpp
#	ggml/src/ggml-cann/kernels/get_row_q4_0.cpp
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
 2024-11-25 16:26:08 +08:00
Georgi Gerganov
d9d54e498d
speculative : refactor and add a simpler example (#10362) 
* speculative : refactor and add a simpler example

ggml-ci

* speculative : clean-up and add comments and TODOs [no ci]

* speculative : manage context in common_speculative

ggml-ci

* speculative : simplify

ggml-ci

* speculative : simplify (cont)

ggml-ci

* speculative : add --draft-min CLI arg

* speculative : minor fixup

* make : build fixes

* speculative : do not redraft previous drafts

ggml-ci

* speculative : fix the draft sampling

ggml-ci

* speculative : fix compile warning

* common : refactor args

ggml-ci

* common : change defaults [no ci]

* common : final touches

ggml-ci
 2024-11-25 09:58:41 +02:00
Concedo
091a432cf6 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-intel.Dockerfile
#	.devops/llama-cli-musa.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-musa.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	cmake/llama-config.cmake.in
#	docs/backend/SYCL.md
#	docs/build.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
 2024-11-21 16:26:24 +08:00
Concedo
282a647689 Merge commit '467576b6cc' into concedo_experimental 
# Conflicts:
#	.gitignore
#	Makefile
#	README.md
#	common/common.h
#	docs/build.md
#	examples/infill/infill.cpp
#	examples/perplexity/perplexity.cpp
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.sh
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-opt.cpp
#	tests/test-quantize-perf.cpp
 2024-11-21 16:05:21 +08:00
Georgi Gerganov
8e752a777b
llama : add check for KV cache shifts (#10401) 
ggml-ci
 2024-11-19 13:29:26 +02:00
Johannes Gäßler
4e54be0ec6
llama/ex: remove --logdir argument (#10339) 2024-11-16 23:00:41 +01:00
Concedo
70aee82552 attempts a backflip, but does he stick the landing? 2024-11-16 17:05:45 +08:00
Diego Devesa
ae8de6d50a
ggml : build backends as libraries (#10256) 
* ggml : build backends as libraries

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: R0CKSTAR <xiaodong.ye@mthreads.com>
 2024-11-14 18:04:35 +01:00
Concedo
a244b1ffd2 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	Package.swift
#	ci/run.sh
#	docs/backend/SYCL.md
#	examples/llama-bench/llama-bench.cpp
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	grammars/README.md
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	scripts/sync-ggml.sh
#	tests/run-json-schema-to-grammar.mjs
#	tests/test-backend-ops.cpp
 2024-11-09 13:36:47 +08:00
Georgi Gerganov
5c333e0140
metal : add BF16 support (#8439) 
* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support
 2024-11-06 19:53:51 +02:00
Concedo
bb13925f39 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	CMakePresets.json
#	Makefile
#	Package.swift
#	ci/run.sh
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	flake.lock
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml.c
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-rope.cpp
 2024-11-04 16:54:53 +08:00
Diego Devesa
9f40989351
ggml : move CPU backend to a separate file (#10144) 2024-11-03 19:34:08 +01:00
Concedo
a46f8acd03 note: also has support for completion tokens count 2024-11-01 00:44:14 +08:00
Georgi Gerganov
8d8ff71536
llama : remove Tail-Free sampling (#10071) 
ggml-ci
 2024-10-29 10:42:05 +02:00
wwoodsTM
ff252ea48e
llama : add DRY sampler (#9702) 
* sampling : add DRY sampler (post-refactor)

* DRY: Trying to fix coauthors, removed unneeded line

* DRY: Fixed redundant code

* DRY: Fixed crash issue due to DRY being in chain but uninitialized

---------

Co-authored-by: l3utterfly <gc.pthzfoldr@gmail.com>
Co-authored-by: pi6am <34464159+pi6am@users.noreply.github.com>
 2024-10-25 19:07:34 +03:00
Michael Podvitskiy
d80fb71f8b
llama: string_split fix (#10022) 
* 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
 2024-10-25 17:57:54 +02:00
Concedo
94a5a27b85 Alone in the darkness 
They're coming for you
I know they will try to catch me too
Alone in the darkness
They're calling for you
There's nowhere to run for cover
 2024-10-24 22:29:20 +08:00
Georgi Gerganov
f594bc80ba
ggml : add asserts for type conversion in fattn kernels (#9971) 
ggml-ci
 2024-10-21 16:20:46 +03:00
Xuan Son Nguyen
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) 
* refactor llama_batch_get_one

* adapt all examples

* fix simple.cpp

* fix llama_bench

* fix

* fix context shifting

* free batch before return

* use common_batch_add, reuse llama_batch in loop

* null terminated seq_id list

* fix save-load-state example

* fix perplexity

* correct token pos in llama_batch_allocr
 2024-10-18 23:18:01 +02:00
Concedo
a9dbcdd3ec Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	docs/build.md
#	examples/infill/infill.cpp
#	examples/main/README.md
#	examples/server/README.md
#	flake.lock
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-sampling.cpp
 2024-10-17 16:36:02 +08:00
MaggotHATE
fbc98b748e
sampling : add XTC sampler (#9742) 
* 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
 2024-10-15 12:54:55 +02:00
Georgi Gerganov
11ac9800af
llama : improve infill support and special token detection (#9798) 
* 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
 2024-10-12 08:21:51 +03:00
Concedo
e692a79aab Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	docs/android.md
#	docs/docker.md
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/infill/infill.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/main/README.md
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/quantize-stats/quantize-stats.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/server/README.md
#	examples/simple/CMakeLists.txt
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-blas.cpp
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	scripts/debug-test.sh
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
#	tests/test-tokenizer-0.cpp
#	tests/test-tokenizer-1-bpe.cpp
#	tests/test-tokenizer-1-spm.cpp
 2024-10-11 11:59:59 +08:00
Diego Devesa
7eee341bee
common : use common_ prefix for common library functions (#9805) 
* common : use common_ prefix for common library functions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-10-10 22:57:42 +02:00
Concedo
da6cf261a8 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	README.md
#	ci/run.sh
#	examples/server/README.md
#	ggml/src/ggml-cuda.cu
#	ggml/src/ggml-metal.m
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
 2024-10-05 22:24:08 +08:00
Georgi Gerganov
8c475b97b8
rerank : use [SEP] token instead of [BOS] (#9737) 
* 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
 2024-10-05 15:55:04 +03:00
Concedo
ce7f9c9a2c Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/python-type-check.yml
#	CMakeLists.txt
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	examples/server/README.md
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/ggml.c
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/sync-ggml.last
#	src/llama-vocab.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-tokenizer-0.cpp
 2024-10-02 01:00:57 +08:00
matiaslin
faac0bae26
common : ensure llama_batch size does not exceed max size (#9668) 
A crash was observed when the number of tokens added to a batch exceeds
llama_batch size. An assertion in llama_batch_add was added to protect
against llama_batch size overflow.
 2024-09-29 15:25:00 +03:00
Georgi Gerganov
f4d2b8846a
llama : add reranking support (#9510) 
* py : add XLMRobertaForSequenceClassification [no ci]

* py : fix scalar-tensor conversion [no ci]

* py : fix position embeddings chop [no ci]

* llama : read new cls tensors [no ci]

* llama : add classigication head (wip) [no ci]

* llama : add "rank" pooling type

ggml-ci

* server : add rerank endpoint

ggml-ci

* llama : aboud ggml_repeat during classification

* rerank : cleanup + comments

* server : accept /rerank endpoint in addition to /v1/rerank [no ci]

* embedding : parse special tokens

* jina : support v1 reranker

* vocab : minor style

ggml-ci

* server : initiate tests for later

ggml-ci

* server : add docs

* llama : add comment [no ci]

* llama : fix uninitialized tensors

* ci : add rerank tests

ggml-ci

* add reranking test

* change test data

* Update examples/server/server.cpp

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

* add `--reranking` argument

* update server docs

* llama : fix comment [no ci]

ggml-ci

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
 2024-09-28 17:42:03 +03:00