nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity
2,249 Commits 1 Branch 0 Tags
15499eb94227401bdc8875da6eb85c15d37068f7
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Georgi GerganovandGitHub 96633eeca1 gemma : use more bits for the token_embd.weight tensor (#5650) 
* gemma : use Q8_0 for the token_embd.weight tensor

* llama : quantize token_embd.weight using output type
 2024-02-22 23:23:46 +02:00
Georgi GerganovGitHubAarni KoskelaJared Van Bortel
 		847eedbdb2 py : add Gemma conversion from HF models (#5647) 
* py : add gemma conversion from HF models

* Update convert-hf-to-gguf.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update convert-hf-to-gguf.py

Co-authored-by: Aarni Koskela <akx@iki.fi>

* Update convert-hf-to-gguf.py

Co-authored-by: Jared Van Bortel <jared@nomic.ai>

---------

Co-authored-by: Aarni Koskela <akx@iki.fi>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-02-22 23:22:48 +02:00
Georgi GerganovandGitHub 7e4f339c40 ggml : always define ggml_fp16_t as uint16_t (#5666) 
* ggml : always define ggml_fp16_t as uint16_t

ggml-ci

* ggml : cont

ggml-ci

* ggml : cont

* ggml : cont

ggml-ci

* ggml : cont

ggml-ci

* cuda : no longer ggml headers last

ggml-ci

* ggml : fix q6_K FP16 -> FP32 conversion

ggml-ci

* ggml : more FP16 -> FP32 conversion fixes

ggml-ci
 2024-02-22 23:21:39 +02:00
Georgi Gerganov 334f76fa38 sync : ggml 2024-02-22 23:21:05 +02:00
Georgi Gerganov efd56b1c21 ggml : 32-bit arm compat (whisper/1891) 
* ggml : 32-bit arm compat

* ggml : add ggml_vqtbl1q_s8 impl

* ggml : cont
 2024-02-22 23:20:50 +02:00
Georgi GerganovandGitHub 5a9e2f60ba py : minor fixes (#5668) 2024-02-22 20:13:25 +02:00
Georgi Gerganov 3a03541ced minor : fix trailing whitespace (#5638) 2024-02-22 13:54:03 +02:00
Georgi GerganovandGitHub 56d03d92be readme : update hot topics 2024-02-22 10:35:54 +02:00
Georgi Gerganov 5022cf242d sync : ggml 2024-02-21 16:52:52 +02:00
Georgi GerganovGitHubbssrdfbssrdf
 		eccd7a26dd sync : ggml (#5633) 
* ggml : fix conv_2d batch mode (ggml/737)

Co-authored-by: bssrdf <bssrdf@gmail.com>

* ggml : compute forward no longer pass src tensors (ggml/729)

* sync : ggml

ggml-ci

---------

Co-authored-by: bssrdf <merlintiger@hotmail.com>
Co-authored-by: bssrdf <bssrdf@gmail.com>
 2024-02-21 16:17:10 +02:00
Georgi GerganovandGitHub c14f72db9c readme : update hot topics 2024-02-21 15:39:54 +02:00
Georgi Gerganov 1387cf60f7 llava : remove extra cont (#5587) 2024-02-19 15:23:17 +02:00
Georgi Gerganov 337c9cbd52 sync : ggml 
ggml-ci
 2024-02-19 15:09:43 +02:00
Georgi Gerganov a3145bdc30 ggml-alloc : apply ggml/731 2024-02-19 15:09:43 +02:00
Georgi GerganovandGitHub d0e3ce51f4 ci : enable -Werror for CUDA builds (#5579) 
* cmake : pass -Werror through -Xcompiler

ggml-ci

* make, cmake : enable CUDA errors on warnings

ggml-ci
 2024-02-19 14:45:41 +02:00
Georgi Gerganov 68a6b98b3c make : fix CUDA build (#5580) 2024-02-19 13:41:51 +02:00
Georgi Gerganov f53119cec4 minor : fix trailing whitespace (#5538) 2024-02-19 10:34:10 +02:00
Georgi Gerganov 14278f55d2 ggml : restore vec dot stride arg names (#5453) 2024-02-18 22:58:57 +02:00
Georgi GerganovandGitHub b1de96824b ci : fix wikitext url + compile warnings (#5569) 
ggml-ci
 2024-02-18 22:39:30 +02:00
Georgi Gerganov 7ad554f90e metal : fix unused warnings (#0) 2024-02-18 21:39:58 +02:00
Georgi Gerganov 689a091bbe sampling : do not set min_keep to n_probs (#5564) 2024-02-18 19:38:06 +02:00
Georgi Gerganov f3f28c5395 cmake : fix GGML_USE_SYCL typo (#5555) 2024-02-18 19:17:00 +02:00
Georgi Gerganov 1dcc3fde00 common : fix ub (#5530) 2024-02-18 18:21:52 +02:00
Georgi GerganovGitHubslaren
 		8f1be0d42f ggml : add ALiBi support for ggml_soft_max_ext (#5488) 
* ggml : avoid recomputing alibi slopes (CPU)

* llama : reuse hparams.f_max_alibi_bias in all cases

ggml-ci

* ggml : support alibi bias in ggml_soft_max_ext (CPU + Metal)

ggml-ci

* ggml : handle all SRCs (do not break on first null)

ggml-ci

* tests : do not use slope for large soft_max

accumulates too much error

ggml-ci

* ggml : alternative ALiBi without extra tensor

We compute the slopes in the kernel

ggml-ci

* cuda : add ALiBi support in ggml_soft_max_ext

ggml-ci

* ggml : deprecate ggml_alibi

* ggml : support multi-sequence ALiBi (Metal)

ggml-ci

* cuda : add multi-seq ALiBi + remote F16 soft_max

ggml-ci

* ggml : update deprecation message

* ggml : fix pos ptr when no ALiBi

ggml-ci

* cuda : fix performance (pow -> powf)

* cuda : precompute ALiBi constants

* metal : pre-compute ALiBi slopes

ggml-ci

* llama : init kq_pos only if needed

ggml-ci

* test-backend-ops : add null pos test to soft_max

test-backend-ops : replace soft_max tests

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-02-17 23:04:16 +02:00
Georgi GerganovandGitHub 5bf2b94dd4 cmake : fix VULKAN and ROCm builds (#5525) 
* cmake : fix VULKAN and ROCm builds

* cmake : fix (cont)

* vulkan : fix compile warnings

ggml-ci

* cmake : fix

ggml-ci

* cmake : minor

ggml-ci
 2024-02-16 19:05:56 +02:00
Georgi GerganovGitHubslaren
 		d2819d5577 scripts : add helpers script for bench comparing commits (#5521) 
* scripts : add helpers script for bench comparing commits

* scripts : detect CUDA

* set flags after checking the command line

* fix make flags

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-02-16 15:14:40 +02:00
Georgi Gerganov 594845aab1 ci : fix BERT model download and convert 2024-02-16 09:57:55 +02:00
Georgi Gerganov c06e45d729 clip : fix wrong loop condition 2024-02-15 18:49:08 +02:00
Georgi GerganovandGitHub 9350a1cf21 scripts : add hf.sh helper script (#5501) 
* scripts : add hf.sh helper scripts

* hf : add error logs

* hf : add support for --repo and --file
 2024-02-15 15:41:15 +02:00
Georgi GerganovandGitHub cf45252a7c tests : multi-thread the tokenizer tests (#5474) 
* tests : multi-thread the tokenizer tests

ggml-ci

* unicode : fix data race for unidentified codepoints

ggml-ci

* unicode : minor style fixes

ggml-ci
 2024-02-13 15:14:22 +02:00
Georgi GerganovandGitHub 49cc1f7d67 bert : add tests + fix quantization (#5475) 
* llama : do not quantize pos embd and token type tensors

* ci : add BERT tests

ggml-ci

* ci : do not do BERT tests on low-perf nodes

ggml-ci
 2024-02-13 13:01:29 +02:00
Georgi GerganovandGitHub 99b8b43d7b tests : disable moe test (#5473) 2024-02-13 11:20:24 +02:00
Georgi Gerganov 099afc6274 llama : fix quantization when tensors are missing (#5423) 2024-02-12 20:14:39 +02:00
Georgi GerganovandGitHub df334a1125 swift : package no longer use ggml dependency (#5465) 
* Revert "swift : update Package.swift to use ggml as dependency (#4691)"

This reverts commit ece9a45e8f.

* spm : add ggml headers
 2024-02-12 19:54:29 +02:00
Georgi GerganovGitHubslaren
 		3b169441df sync : ggml (#5452) 
* ggml-alloc : v3 (ggml/727)

* ggml-alloc v3

ggml-ci

* fix ci

ggml-ci

* whisper : check for backend buffer allocation failures

* whisper : avoid leaks when initialization fails

* cleanup

ggml-ci

* style fixes

ggml-ci

* sync : ggml

* update llama.cpp, clip.cpp, export-lora.cpp

* update finetune.cpp, train-text-from-scratch.cpp

ggml-ci

* ggml-backend : reduce alignment to 32 to match gguf and fix mmap

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-02-12 09:16:06 +02:00
Georgi Gerganov 85910c5b30 main : ctrl+C print timing in non-interactive mode (#3873) 2024-02-11 15:35:50 +02:00
Georgi Gerganov 139b62a839 common : fix compile warning 2024-02-11 15:33:43 +02:00
Georgi Gerganov 0f2411f154 ggml : fix compile warnings (unused vars) (#4966) 2024-02-11 15:33:01 +02:00
Georgi Gerganov cd9aea63b5 scripts : update sync scripts with new backends 2024-02-10 09:53:05 +02:00
Georgi Gerganov 43b65f5eb8 sync : ggml 2024-02-10 09:30:36 +02:00
Georgi Gerganov 8504d2d0da tests : .gitignore obj files 2024-02-08 09:46:47 +02:00
Georgi GerganovandGitHub 906cff55c2 py : handle byte tokens in get_token_type (#5341) 
* py : handle byte tokens in `get_token_type`

* py : fix empty bytes arg
 2024-02-06 07:47:22 +02:00
Georgi Gerganov 30679d438d scripts : fix typos, cleanup (#5303) 2024-02-05 09:48:03 +02:00
Georgi GerganovandGitHub e437b37fd0 scripts : parse wtype in server-llm.sh (#5167) 
* scripts : parse wtype in server-llm.sh

* scripts : fix check for wfile
 2024-02-02 14:23:40 +02:00
Georgi Gerganov d3bac7d584 llama : reorder build_orion() at correct place (#5118) 2024-01-31 18:47:10 +02:00
Georgi GerganovGitHubslaren
 		5cb04dbc16 llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240) 
* llama : remove LLAMA_MAX_DEVICES from llama.h

ggml-ci

* Update llama.cpp

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

* server : remove LLAMA_MAX_DEVICES

ggml-ci

* llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD

ggml-ci

* train : remove LLAMA_SUPPORTS_GPU_OFFLOAD

* readme : add deprecation notice

* readme : change deprecation notice to "remove" and fix url

* llama : remove gpu includes from llama.h

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-01-31 17:30:17 +02:00
Georgi Gerganov efb7bdbbd0 metal : add im2col F32 dst support (#5132) 2024-01-31 15:35:41 +02:00
Georgi Gerganov e0085fdf7c Revert "server : change deps.sh xxd files to string literals (#5221)" 
This reverts commit 4003be0e5f.
 2024-01-30 21:19:26 +02:00
Georgi GerganovandGitHub e6f291d158 server : fix context shift (#5195) 
* server : fix context shift + simplify self-extend

* server : take system_tokens into account

* server : more n_past fixes

* server : rever n_past_se changes
 2024-01-30 20:17:30 +02:00
Georgi Gerganov 8f8ddfcfad sync : ggml (#0) 2024-01-30 16:21:57 +02:00
Georgi Gerganov 6fb50ebbf0 gguf : fix comparison (ggml/715) 
ggml-ci
 2024-01-30 16:20:25 +02:00
Georgi Gerganov a4b07c057a gguf : add input validation, prevent integer overflows (ggml/709) 
* gguf : add input validation, prevent integer overflows

ggml-ci

* gguf : fix switch default case

* gguf : sanitize info->n_dims and info->type

ggml-ci

* gguf : assert GGUF_TYPE_SIZE access

ggml-ci

* ggml : assert mallocs are successful

ggml-ci

* gguf : prevent integer overflow

* gguf : sanitize tensor info

ggml-ci

* gguf : stricter limit on the number of items

ggml-ci
 2024-01-30 16:20:25 +02:00
Georgi Gerganov 549a1e6cd5 ci : fix yolo URLs + fix metal capture (ggml/712) 2024-01-30 16:20:25 +02:00
Georgi GerganovandGitHub 49f44b5c55 readme : update hot topics 2024-01-30 11:14:44 +02:00
Georgi GerganovandGitHub 14fef85e2d py : fix except (#5194) 
ggml-ci
 2024-01-29 15:35:54 +02:00
Georgi Gerganov 35dec26cc2 sync : ggml 2024-01-28 19:48:05 +02:00
Georgi Gerganov d460510c72 ggml : minor type fix (int64_t -> size_t) 2024-01-28 19:47:31 +02:00
Georgi GerganovandGitHub b764b8f1d0 flake.lock: Update (#5162) 2024-01-28 14:54:54 +00:00
Georgi Gerganov 753eafed0e sync : ggml 2024-01-27 17:00:24 +02:00
Georgi Gerganov 5f1925a8ce scripts : move run-with-preset.py from root to scripts folder 2024-01-26 17:09:44 +02:00
Georgi Gerganov 3b7c914de2 tests : gitignore test-c.o 2024-01-26 14:48:15 +02:00
Georgi GerganovandGitHub aad0b01d73 readme : update hot topics 2024-01-26 10:52:33 +02:00
Georgi Gerganov ddc5a5033f metal : show compile log messages 2024-01-25 11:26:17 +02:00
Georgi Gerganov 26d607608d metal : disable support for MUL_MAT F32 x F16 2024-01-23 15:50:56 +02:00
Georgi GerganovandGitHub 89758723c7 minor : clean-up some warnings and style (#5094) 
* minor : clean-up some warnings and style

ggml-ci

* ggml : add comment
 2024-01-23 14:12:57 +02:00
Georgi GerganovGitHubgithub-actions[bot] <github-actions[bot]@users.noreply.github.com>
 		942c0107a7 flake.lock: Update (#5054) 
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/9b19f5e77dd906cb52dade0b7bd280339d2a1f3d' (2024-01-13)
  → 'github:NixOS/nixpkgs/bbe7d8f876fbbe7c959c90ba2ae2852220573261' (2024-01-19)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2024-01-21 03:17:27 +00:00
Georgi GerganovandGitHub a5cacb22b2 imatrix : add README.md 2024-01-19 15:24:47 +02:00
Georgi Gerganov de9a147df1 py : fix flake8 lint 2024-01-19 13:52:22 +02:00
Georgi GerganovandGitHub 8b20858e5e perplexity : faster Winogrande via batching (#5024) 
* perplexity : faster Winogrande via batching

ggml-ci

* perplexity : remove unused function

* perplexity : only tokenize selected tasks for Winogrande
 2024-01-19 10:45:06 +02:00
Georgi Gerganov 9b6ea4263a cmake : add ggml public headers (#5011) 2024-01-18 23:36:07 +02:00
Georgi Gerganov 2d5419d08a imatrix : fix assert for src0 non-cont check 2024-01-18 21:45:51 +02:00
Georgi Gerganov d391ae9b49 perplexity : fix winogrande N tasks option 2024-01-18 20:49:00 +02:00
Georgi Gerganov e9240cdfa0 scripts : add get-winogrande.sh 2024-01-18 20:45:39 +02:00
Georgi GerganovandGitHub ad19812cda perplexity : faster HellaSwag via batching (#5017) 
* perplexity : faster HellaSwag

ggml-ci

* perplexity : clean-up

ggml-ci

* perplexity : no need for decode_helper

ggml-ci

* perplexity : add comments

* perplexity : option to specify max batched tasks via `n_parallel`

* perplexity : remove HellaSwag restruction for n_batch
 2024-01-18 15:33:01 +02:00
Georgi Gerganov dcad445d0c scritps : add helper script to get hellaswag data in txt format 2024-01-18 11:44:49 +02:00
Georgi Gerganov 6b6916b215 sync : ggml 2024-01-17 20:54:50 +02:00
Georgi GerganovandGitHub 38566680cd ggml : add IQ2 to test-backend-ops + refactoring (#4990) 
* ggml : add IQ2 to test-backend-ops + refactoring

ggml-ci

* cuda : update supports_op for IQ2

ggml-ci

* ci : enable LLAMA_CUBLAS=1 for CUDA nodes

ggml-ci

* cuda : fix out-of-bounds-access in `mul_mat_vec_q`

ggml-ci

* tests : avoid creating RNGs for each Q tensor

ggml-ci

* tests : avoid creating RNGs for each tensor

ggml-ci
 2024-01-17 18:54:56 +02:00
Georgi GerganovandGitHub ba69bbc84c imatrix : offload to GPU support (#4957) 
* backend : add eval callback

ggml-ci

* backend : group nodes in a single compute when user don't need them

* backend : clean-up the implementation

ggml-ci

* simple : do not perform tensor data copy if not needed

* simple : fix

* imatrix : offload to GPU support

* imatrix : fix ggml_mul_mat_id hanlding

ggml-ci

* ci : add imatrix test

ggml-ci

* ci : rearrange output

ggml-ci
 2024-01-17 18:46:30 +02:00
Georgi GerganovandGitHub 44a1a4a41a backend : add eval callback (#4935) 
* backend : add eval callback

ggml-ci

* backend : group nodes in a single compute when user don't need them

* backend : clean-up the implementation

ggml-ci

* simple : do not perform tensor data copy if not needed

* simple : fix

* simple : no need for ggml_is_contiguous + fix bool parse

* llama : fix callback placement in llama_context_params

* backend : avoid double-ask callback calls

* simple : restore examples, imatrix will serve as a demo
 2024-01-17 18:39:41 +02:00
Georgi GerganovandGitHub c918fe8dca metal : create autorelease pool during library build (#4970) 
* metal : create autorelease pool during library build

ggml-ci

* test : simplify

ggml-ci
 2024-01-17 18:38:39 +02:00
Georgi Gerganov 0f83e727af py : fix whitespace 2024-01-17 18:37:36 +02:00
Georgi GerganovandGitHub 4f4bf35f46 py : fix missing added_tokens_dict for SPM and BPE vocabs (#4971) 
* py : fix missing added_tokens_dict for SPM vocab

* py : pad with unknown tokens when data is missing

ggml-ci

* py : fix BPE vocab conversion

ggml-ci

* py : fix padded dummy tokens (I hope)
 2024-01-17 15:45:03 +02:00
Georgi Gerganov 5c99960901 py : remove unnecessary hasattr (#4903) 2024-01-16 20:59:31 +02:00
Georgi GerganovandGitHub 959ef0c0df perplexity : fix kv cache handling for hellaswag (#4981) 
ggml-ci
 2024-01-16 19:34:54 +02:00
Georgi GerganovGitHubgithub-actions[bot] <github-actions[bot]@users.noreply.github.com>
 		c37b3474e6 flake.lock: update flake-parts, flake-parts/nixpkgs-lib, and nixpkgs (#4920) 
Flake lock file updates:

• Updated input 'flake-parts':
    'github:hercules-ci/flake-parts/34fed993f1674c8d06d58b37ce1e0fe5eebcb9f5' (2023-12-01)
  → 'github:hercules-ci/flake-parts/07f6395285469419cf9d078f59b5b49993198c00' (2024-01-11)
• Updated input 'flake-parts/nixpkgs-lib':
    'github:NixOS/nixpkgs/e92039b55bcd58469325ded85d4f58dd5a4eaf58?dir=lib' (2023-11-29)
  → 'github:NixOS/nixpkgs/b0d36bd0a420ecee3bc916c91886caca87c894e9?dir=lib' (2023-12-30)
• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/cfc3698c31b1fb9cdcf10f36c9643460264d0ca8' (2023-12-27)
  → 'github:NixOS/nixpkgs/317484b1ead87b9c1b8ac5261a8d2dd748a0492d' (2024-01-08)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2024-01-16 09:13:54 -08:00
Georgi Gerganov ddb008d845 cuda : fix dequantize kernel names (#4938) 2024-01-15 13:27:00 +02:00
Georgi GerganovandGitHub bb0c139247 llama : check LLAMA_TRACE env for extra logging (#4929) 
* llama : minor fix indent

* llama : check LLAMA_TRACE env for extra logging

ggml-ci
 2024-01-14 13:26:53 +02:00
Georgi Gerganov 9408cfdad6 scripts : sync-ggml-am.sh option to skip commits 2024-01-14 11:08:41 +02:00
Georgi Gerganov 03c5267490 llama : use LLAMA_LOG_ macros for logging 2024-01-14 11:03:19 +02:00
Georgi Gerganov 76484fbfd3 sync : ggml 2024-01-14 00:14:46 +02:00
Georgi GerganovandGitHub 4be5ef556d metal : remove old API (#4919) 
ggml-ci
 2024-01-13 20:45:45 +02:00
Georgi GerganovandGitHub 0ea069b87b server : fix prompt caching with system prompt (#4914) 2024-01-13 19:31:26 +02:00
Georgi GerganovGitHubgoerch
 		f172de03f1 llama : fix detokenization of non-special added-tokens (#4916) 
Co-authored-by: goerch <jhr.walter@t-online.de>
 2024-01-13 18:47:38 +02:00
Georgi Gerganov 2d57de5255 metal : disable log for loaded kernels (#4794) 2024-01-13 18:46:37 +02:00
Georgi GerganovandGitHub b38b5e93ae metal : refactor kernel loading code (#4794) 
* metal : detect more GPU families

* metal : refactor kernel loading

* metal : set kernel family requirements

* metal : fix kernel init + fix compile options

* metal : take into account simdgroup reduction support

* metal : print only skipped kernels

* metal : fix check for simdgroup reduction support

* metal : check for Metal 3

* metal : free allocations

* metal : normalize encoder:setComputePipelineStatus calls

ggml-ci

* metal : fix Metal3 family check

ggml-ci

* metal : check for simdgroup matrix mul. feature

ggml-ci
 2024-01-13 18:03:45 +02:00
Georgi GerganovandGitHub 15ebe59210 convert : update phi-2 to latest HF repo (#4903) 
* convert : update phi-2 to latest HF repo

ggml-ci

* py : try to fix flake stuff
 2024-01-13 13:44:37 +02:00
Georgi Gerganov de473f5f8e sync : ggml 2024-01-12 22:02:43 +02:00
Georgi Gerganov f238461236 ggml : fix 32-bit ARM compat for IQ2_XS (whisper/1758) 
* ggml : fix 32-bit ARM compat

* ggml : fix fix

* ggml : fix fix fix
 2024-01-12 22:02:11 +02:00
Georgi Gerganov 584d674be6 llama : remove redundant assert for StableLM (#4901) 2024-01-12 20:54:12 +02:00
Georgi Gerganov 5537d9d36b gitignore : imatrix 2024-01-12 14:33:21 +02:00