vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
2537 commits 380 branches 3056 tags 365 MiB
Commit graph

2537 commits

This branch
This branch
All branches
Author SHA1 Message Date
Georgi Gerganov
9a3b4f6c86
ggml : fix UNUSED macro (#3762) 2023-11-01 13:50:45 +02:00
Andrew Godfrey
73bdcb395e
finetune : add -ngl parameter (#3762) 
* Add '-ngl' support to finetune.cpp

* Add fprintf in ggml_cuda_op_add

When I tried CUDA offloading during finetuning following the readme, I got an assert here.
This probably isn't an important case because inference later gives a warning saying you should use f16 or f32 instead when using lora

* Add 'finetune.sh', which currently fails when using GPU

"error: operator (): Finetuning on tensors with type 'f16' is not yet supported"

* tweak finetune.sh

* Suppress some warnings in ggml.c

* Add f16 implementation to ggml_compute_forward_add_f16_f32

* Add an f16 case to ggml_add_cast_impl and llama_build_lora_finetune_graphs

* finetune.sh: Edit comments

* Add "add_f16_f32_f32_cuda"

* Tweak an error message

* finetune.sh: Add an optional LLAMA_MODEL_DIR variable

* finetune.sh: Add an optional LLAMA_TRAINING_DIR variable

* train : minor

* tabs to spaces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
 2023-11-01 13:49:04 +02:00
Concedo
ae2cd56de8 kobold integration of min_p sampler (+1 squashed commits) 
Squashed commits:

[8ad2e349] kobold integration for min_p sampler
 2023-11-01 19:08:45 +08:00
Concedo
bcb397953f Merge remote-tracking branch 'llama.cpp/try-fix-3869' into concedo_experimental 2023-11-01 18:29:08 +08:00
Concedo
92d80b94b3 bundle simpleclinfo into pyinstaller except for linux 2023-11-01 18:26:15 +08:00
Concedo
9342636408 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	flake.lock
#	flake.nix
 2023-11-01 18:24:36 +08:00
Concedo
df7e757d40 windows: added simpleclinfo, which helps determine clblast platform and device on windows 2023-11-01 18:10:35 +08:00
Georgi Gerganov
f0e209324a
scripts : add server-llm.sh (#3868) 
* scripts : add deploy-server.sh

* scripts : rename to server-llm.sh

* scripts : working curl pipe
 2023-11-01 11:29:07 +02:00
Adrian Hesketh
ca190bca8e
server : re-enable completion and embedded at the same time (#3876) 2023-11-01 11:28:28 +02:00
Georgi Gerganov
71e3718abd
llama : refactor graph build code (#3837) 
* llama : factor out ggml-alloc from graph graph build functions

ggml-ci

* metal : disable kernel load log

* llama : factor out tensor offloading outside the build call (wip)

ggml-ci

* llama : offload rest of the models

ggml-ci

* llama : update offload log messages to print node index

* llama : comments

* llama : support offloading result_norm + comments

* llama : factor graph input into a function

* llama : do tensor offload only with CUDA

* llama : fix res_norm offloading

* llama : try to optimize offloading code

* llama : fix non-CUDA build

* llama : try to fix build

* llama : move refact in correct place + optimize graph input

* llama : refactor tensor offloading as callback

* llama : add layer index to all tensor names

* llama : add functional header

* llama : comment

ggml-ci

* llama : remove obsolete map for layer counting

* llama : add llm_build helper functions (#3848)

* llama : add llm_build_norm helper function

ggml-ci

* llama : add llm_build_ffn helper function (#3849)

ggml-ci

* llama : add llm_build_k_shift helper

ggml-ci

* llama : fix offloading after recent changes

* llama : add llm_build_kv_store helper

ggml-ci

* llama : remove obsolete offload names

* llama : fix llm_build_k_shift to use n_head_kv instead of n_head

* llama : simplify falcon Q, K, V computation

* llama : remove obsolete comments in build graphs

* llama : add llm_build_kqv helper

ggml-ci

* llama : minor

* llama : add LLAMA_OFFLOAD_DEBUG + fix starcoder offloading

* llama : fix input allocation logic

* llama : update offload functions for KQ tensors

* llama : normalize tensor names

ggml-ci

* llama : enable warning about not offloaded tensors

* llama : remove extra ; + deduplicate gate_b logic

* llama : add llm_build_inp_embd helper
 2023-11-01 08:04:02 +02:00
kalomaze
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841) 
* Introduce the new Min-P sampler by @kalomaze
   The Min-P sampling method was designed as an alternative to Top-P, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token.

* Min-P enabled and set to 0.05 default

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
 2023-10-31 20:44:49 +01:00
Georgi Gerganov
22cc9bef09
cuda : check if this fixes Pascal card regression 2023-10-31 20:01:47 +02:00
Tungsten842
07178c98e1
flake.nix: fix for rocm 5.7 (#3853) 2023-10-31 19:24:03 +02:00
Concedo
43a5143450 added clinfo binary, cleanup unused stuff 2023-10-31 22:25:25 +08:00
Concedo
f3690ba6d2 shifting enabled by default 2023-10-31 21:41:57 +08:00
Concedo
e62f38abd1 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	tests/test-double-float.cpp
#	tests/test-quantize-fns.cpp
 2023-10-31 21:09:49 +08:00
Concedo
cc5b282350 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	build.zig
#	flake.lock
#	flake.nix
#	ggml.c
 2023-10-31 20:44:04 +08:00
Georgi Gerganov
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861) 
* ggml : move FP16 <-> FP32 stuff to ggml-impl.h

ggml-ci

* tests : fix ARM build

* ggml : explicitly initialize deprecated type traits

* ggml : add math.h to ggml-impl.h

* ggml : remove duplicate static assert macros

* ggml : prefix lookup tables with ggml_

ggml-ci

* ggml-impl : move extern "C" to start of file
 2023-10-30 19:19:15 +02:00
Concedo
9eba77c6a0 finally got something workable 2023-10-30 23:30:21 +08:00
Concedo
61c395833d context shifting is still buggy 2023-10-30 16:25:01 +08:00
Kerfuffle
6e08281e58
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843) 
* Extend llama_kv_cache_seq_rm to allow matichng any sequence

* Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear

Use llama_kv_cache_clear for cache clearing

Change calls to llama_kv_cache_tokens_rm that want to delete by position to use llama_kv_cache_seq_rm functionality
 2023-10-29 11:31:40 -06:00
cebtenzzre
2046eb4345
make : remove unnecessary dependency on build-info.h (#3842) 2023-10-29 18:33:47 +02:00
Georgi Gerganov
71a09da301
llama : fix kv shift bug (#3835) 
ggml-ci
 2023-10-29 18:32:51 +02:00
Georgi Gerganov
d69d777c02
ggml : quantization refactoring (#3833) 
* ggml : factor all quantization code in ggml-quants

ggml-ci

* ggml-quants : fix Zig and Swift builds + quantize tool

ggml-ci

* quantize : --pure option for disabling k-quant mixtures

---------

Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
 2023-10-29 18:32:28 +02:00
Concedo
7f5d1b2fc6 slider error 2023-10-30 00:02:38 +08:00
Concedo
7f050b5d16 tweak numbers 2023-10-29 22:46:19 +08:00
Concedo
7924592a83 context shift feature done 2023-10-29 18:21:39 +08:00
Concedo
338d6c265d fixes to smartcontextpro 2023-10-29 10:42:37 +08:00
Erik Scholz
ff3bad83e2
flake : update flake.lock for newer transformers version + provide extra dev shell (#3797) 
* flake : update flake.lock for newer transformers version + provide extra dev shell with torch and transformers (for most convert-xxx.py scripts)
 2023-10-28 16:41:07 +02:00
Aarni Koskela
82a6646e02
metal : try cwd for ggml-metal.metal if bundle lookup fails (#3793) 
* Try cwd for ggml-metal if bundle lookup fails

When building with `-DBUILD_SHARED_LIBS=ON -DLLAMA_METAL=ON -DLLAMA_BUILD_SERVER=ON`,
`server` would fail to load `ggml-metal.metal` because `[bundle pathForResource:...]`
returns `nil`.  In that case, fall back to `ggml-metal.metal` in the cwd instead of
passing `null` as a path.

Follows up on #1782

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-10-28 15:43:01 +03:00
Georgi Gerganov
ba231e8a6d
issues : change label from bug to bug-unconfirmed (#3748) 2023-10-28 15:35:26 +03:00
Georgi Gerganov
8a2f2fea29
convert : ignore tokens if their IDs are within [0, vocab_size) (#3831) 2023-10-28 06:25:15 -06:00
Kerfuffle
bd6d9e2059
llama : allow quantizing k-quants to fall back when tensor size incompatible (#3747) 
* Allow quantizing k-quants to fall back when tensor size incompatible

* quantizing: Add warning when tensors were incompatible with k-quants

Clean up k-quants state passing a bit
 2023-10-28 14:54:24 +03:00
Georgi Gerganov
ee1a0ec9cb
llama : add option for greedy sampling with probs (#3813) 
* llama : add option for greedy sampling with probs

* llama : add comment about llama_sample_token_greedy() missing probs

* sampling : temp == 0.0 -> no probs, temp < 0.0 -> probs
 2023-10-28 14:23:11 +03:00
Concedo
20ef442c2a fixed for smartcontext 2023-10-28 19:09:22 +08:00
Henk Poley
177461104b
common : print that one line of the syntax help *also* to standard output (#3823) 2023-10-28 13:16:33 +03:00
Concedo
6cf2b4c73b MMQ optimizations (+1 squashed commits) 
Squashed commits:

[d87de001] mmq optimization (+1 squashed commits)

Squashed commits:

[f1f67af8] still allow mmq
 2023-10-28 17:57:46 +08:00
Georgi Gerganov
fdee152e4e
starcoder : add GPU offloading (#3827) 
* starcoder : do not GPU split 1D bias tensors

* starcoder : offload layers to GPU

ggml-ci
 2023-10-28 12:06:08 +03:00
Concedo
2ea3b567cf Merge: Testing speed of tensor cores vs MMQ 2023-10-28 16:41:42 +08:00
Concedo
2fa1137890 updated lite 2023-10-28 14:43:15 +08:00
Concedo
09c74ea046 include content-length 2023-10-28 14:24:37 +08:00
Concedo
64f3bc5168 update model string (+1 squashed commits) 
Squashed commits:

[a7c568ea] simplify colab
 2023-10-28 14:07:52 +08:00
Concedo
879d1ba268 simplify colab dropdowns (+1 squashed commits) 
Squashed commits:

[72aab0e8] simplify colab dropdown
 2023-10-28 13:57:01 +08:00
Pyroserenus
eb9a93097b
Colab Improvements (#498) 
* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb

* Update colab.ipynb
 2023-10-28 13:26:59 +08:00
Concedo
15f525c580 revamped smart context for llama models 2023-10-28 12:59:08 +08:00
Kerfuffle
41aee4df82
speculative : ensure draft and target model vocab matches (#3812) 
* speculative: Ensure draft and target model vocab matches

* Tolerate small differences when checking dft vs tgt vocab
 2023-10-28 00:40:07 +03:00
cebtenzzre
6d459cbfbe
llama : correctly report GGUFv3 format (#3818) 2023-10-27 17:33:53 -04:00
Thibault Terrasson
c8d6a1f34a
simple : fix batch handling (#3803) 2023-10-27 08:37:41 -06:00
Georgi Gerganov
2f9ec7e271
cuda : improve text-generation and batched decoding performance (#3776) 
* cuda : prints wip

* cuda : new cublas gemm branch for multi-batch quantized src0

* cuda : add F32 sgemm branch

* cuda : fine-tune >= VOLTA params + use MMQ only for small batches

* cuda : remove duplicated cuBLAS GEMM code

* cuda : add CUDA_USE_TENSOR_CORES and GGML_CUDA_FORCE_MMQ macros

* build : add compile option to force use of MMQ kernels
 2023-10-27 17:01:23 +03:00
Concedo
c2f675133d support for abort without crash on disconnect 2023-10-27 15:27:17 +08:00