nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 21 Packages Projects Releases Wiki Activity
1,783 Commits 1 Branch 0 Tags
3c36213df850a2353e95572b3636797c79b7c815
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Georgi GerganovandGitHub 3c36213df8 llama : remove redundant GQA check (#4796) 2024-01-07 11:21:53 +02:00
Georgi Gerganov d117d4dc5d llama : print tensor meta for debugging 2024-01-07 09:51:12 +02:00
Georgi GerganovandGitHub 67984921a7 server : fix n_predict check (#4798) 2024-01-07 08:45:26 +02:00
Georgi Gerganov 96e80dabc6 examples : improve base-translate.sh script (#4783) 2024-01-06 11:40:24 +02:00
Georgi Gerganov 91d38876df metal : switch back to default.metallib (ggml/681) 
ggml-ci
 2024-01-05 18:02:06 +02:00
Georgi Gerganov d061bf9405 ggml : fix q2_k bpw in comments (ggml/680) 2024-01-05 18:02:06 +02:00
Georgi GerganovandGitHub c1d7cb28d3 ggml : do not sched_yield when calling BLAS (#4761) 
* ggml : do not sched_yield when calling BLAS

ggml-ci

* ggml : fix do_yield logic

ggml-ci

* ggml : simplify do_yield logic

ggml-ci
 2024-01-05 15:18:21 +02:00
Georgi GerganovandGitHub 3681f22443 examples : add few-shot translation example (#4783) 2024-01-05 15:11:10 +02:00
Georgi GerganovandGitHub 012cf349ae server : send token probs for "stream == false" (#4714) 2024-01-04 19:56:33 +02:00
Georgi GerganovandGitHub dc891b7f7a ggml : include stdlib.h before intrin.h (#4736) 2024-01-04 10:12:26 +02:00
Georgi Gerganovandslaren 7bed7eba35 cuda : simplify expression 
Co-authored-by: slaren <slarengh@gmail.com>
 2024-01-03 14:38:38 +02:00
Georgi Gerganov d55356d3ba cuda : mark I16 and I32 ops as unsupported 
ggml-ci
 2024-01-03 14:38:38 +02:00
Georgi Gerganov 75e3fd8581 sync : ggml 
ggml-ci
 2024-01-03 14:38:38 +02:00
Georgi Gerganov 289313716f metal : add kernel_get_rows_i32 
ggml-ci
 2024-01-03 14:38:38 +02:00
Georgi Gerganov ab62fc3e55 scripts : fix sync order + metal sed 2024-01-03 14:38:38 +02:00
Georgi GerganovandGitHub f3f62f0d83 metal : optimize ggml_mul_mat_id (faster Mixtral PP) (#4725) 
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

* metal : optimizing ggml_mul_mat_id (wip)

* metal : minor fix

* metal : opt mul_mm_id
 2024-01-02 21:07:47 +02:00
Georgi Gerganov 540938f890 llama : llama_model_desc print number of experts 2024-01-02 16:26:45 +02:00
Georgi Gerganov 32866c5edd editorconfig : fix whitespace and indentation #4710 2024-01-02 13:28:15 +02:00
Georgi GerganovandGitHub 58ba655af0 metal : enable shader debugging (cmake option) (#4705) 
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

ggml-ci
 2024-01-02 10:57:44 +02:00
Georgi GerganovandGitHub e39106c055 ggml : add ggml_vdotq_s32 alias (#4715) 
ggml-ci
 2023-12-31 11:43:31 +02:00
Georgi GerganovandGitHub 9fbda719de clip : refactor + bug fixes (#4696) 
* clip : refactor + bug fixes

ggml-ci

* server : add log message
 2023-12-30 23:24:42 +02:00
Georgi Gerganov 0235b9b571 clip : use ggml_backend_buffer_is_host (#4205) 2023-12-29 18:53:34 +02:00
Georgi Gerganov c8255f8a6b scripts : print list of sync commits 2023-12-29 15:12:35 +02:00
Georgi Gerganov 38b3de4658 sync : ggml 2023-12-29 14:56:41 +02:00
Georgi Gerganov ca38b8d334 scripts : do not sync commits from this repo 2023-12-29 14:54:05 +02:00
Georgi Gerganov b47879b0dd scripts : add sync-ggml-am.sh 2023-12-27 11:44:22 +02:00
Georgi GerganovandGitHub 951010fa53 ggml : fix dot product for ARM (#4630) 
ggml-ci
 2023-12-27 11:02:13 +02:00
Georgi GerganovGitHubleejet
 		ba66175132 sync : ggml (fix im2col) (#4591) 
* cuda : fix im2col_f32_f16 (ggml/#658)

ggml-ci

* ggml-alloc : fix ggml_tallocr_is_own

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2023-12-22 17:53:43 +02:00
Georgi GerganovandGitHub afefa319f1 ggml : change ggml_scale to take a float instead of tensor (#4573) 
* ggml : change ggml_scale to take a float instead of tensor

* ggml : fix CPU implementation

* tests : fix test-grad0

ggml-ci
 2023-12-21 23:20:49 +02:00
Georgi GerganovandGitHub 769a7bc85e gguf-py : fix broken link 2023-12-21 23:20:36 +02:00
Georgi Gerganov 32259b2dad gguf : simplify example dependencies 2023-12-21 23:08:14 +02:00
Georgi GerganovandGitHub c083718c89 readme : update coding guidelines 2023-12-21 19:27:14 +02:00
Georgi Gerganov 0e18b2e7d0 llama.swiftui : add tinyllama 1.1B F16 2023-12-18 20:17:43 +02:00
Georgi Gerganov 6ff39b129d llama.swiftui : add more models 2023-12-18 20:05:12 +02:00
Georgi GerganovandGitHub b1306c4394 readme : update hot topics 2023-12-17 20:16:23 +02:00
Georgi GerganovGitHubjhen
 		800a489e4a llama.swiftui : add bench functionality (#4483) 
* llama.swiftui : add bench button

* llama.swiftui : initial bench functionality

* force to use n_gpu_layers on simulator

* add download buttons & expose llamaState.loadModel

* update project.pbxproj

* comment #Preview & fix editorconfig check

* gitignore : xcode stuff

* llama.swiftui : UX improvements

* llama.swiftui : avoid data copy via "downloadTask"

* llama.swiftui : remove model from project

* llama : remove "mostly" from model infos

* llama.swiftui : improve bench

---------

Co-authored-by: jhen <developer@jhen.me>
 2023-12-17 19:38:41 +02:00
Georgi Gerganov 55e87c3749 ggml : fix OpenCL broadcast requirement for ggml_mul (close #4453) 2023-12-14 10:35:29 +02:00
Georgi GerganovGitHubslaren
 		4d98d9a656 sync : ggml (SD ops, tests, kernels) (#4444) 
* sync : ggml (SD ops, tests, kernels)

ggml-ci

* cuda : restore im2col

ggml-ci

* metal : fix accuracy of dequantization kernels

ggml-ci

* cuda : restore correct im2col

ggml-ci

* metal : try to fix moe test by reducing expert size

ggml-ci

* cuda : fix bin bcast when src1 and dst have different types

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-12-13 21:54:54 +02:00
Georgi GerganovandGitHub 113f9942fc readme : update hot topics 2023-12-13 14:05:38 +02:00
Georgi GerganovGitHubslaren
 		fe680e3d10 sync : ggml (new ops, tests, backend, etc.) (#4359) 
* sync : ggml (part 1)

* sync : ggml (part 2, CUDA)

* sync : ggml (part 3, Metal)

* ggml : build fixes

ggml-ci

* cuda : restore lost changes

* cuda : restore lost changes (StableLM rope)

* cmake : enable separable compilation for CUDA

ggml-ci

* ggml-cuda : remove device side dequantize

* Revert "cmake : enable separable compilation for CUDA"

This reverts commit 09e35d04b1c4ca67f9685690160b35bc885a89ac.

* cuda : remove assert for rope

* tests : add test-backend-ops

* ggml : fix bug in ggml_concat

* ggml : restore `ggml_get_n_tasks()` logic in `ggml_graph_plan()`

* ci : try to fix macOS

* ggml-backend : remove backend self-registration

* ci : disable Metal for macOS cmake build

ggml-ci

* metal : fix "supports family" call

* metal : fix assert

* metal : print resource path

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-12-07 22:26:54 +02:00
Georgi GerganovGitHubslaren
 		bcc0eb4591 llama : per-layer KV cache + quantum K cache (#4309) 
* per-layer KV

* remove unnecessary copies

* less code duplication, offload k and v separately

* llama : offload KV cache per-layer

* llama : offload K shift tensors

* llama : offload for rest of the model arches

* llama : enable offload debug temporarily

* llama : keep the KV related layers on the device

* llama : remove mirrors, perform Device -> Host when partial offload

* common : add command-line arg to disable KV cache offloading

* llama : update session save/load

* llama : support quantum K cache (#4312)

* llama : support quantum K cache (wip)

* metal : add F32 -> Q8_0 copy kernel

* cuda : add F32 -> Q8_0 copy kernel

ggml-ci

* cuda : use mmv kernel for quantum cache ops

* llama : pass KV cache type through API

* llama : fix build

ggml-ci

* metal : add F32 -> Q4_0 copy kernel

* metal : add F32 -> Q4_1 copy kernel

* cuda : wip

* cuda : add F32 -> Q4_0 and F32 -> Q4_1 copy kernels

* llama-bench : support type_k/type_v

* metal : use mm kernel only for quantum KV cache

* cuda : add comment

* llama : remove memory_f16 and kv_f16 flags

---------

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

* readme : add API change notice

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-12-07 13:03:17 +02:00
Georgi GerganovandGitHub 05cd6e5036 server : recognize cache_prompt parameter in OAI API (#4347) 2023-12-06 20:21:59 +02:00
Georgi Gerganov caa9249217 common : fix compile warning 2023-12-06 10:41:03 +02:00
Georgi GerganovandGitHub fbbc42827b ggml : reuse ggml_get_n_tasks() in ggml_graph_plan() (#4308) 
* ggml : fix soft max out-of-bounds access

ggml-ci

* ggml : reuse ggml_get_n_tasks() in ggml_graph_plan()

ggml-ci
 2023-12-03 15:56:35 +02:00
Georgi GerganovandGitHub adf3de4f69 ggml : fix soft max out-of-bounds access (#4307) 
ggml-ci
 2023-12-03 15:56:22 +02:00
Georgi GerganovandGitHub d7b800b8bc llama : pad KV cache size (#4280) 
* llama : pad KV cache size to 32

* metal : try to improve batched decoding
 2023-12-03 10:58:16 +02:00
Georgi Gerganov 5a7d3125e7 llama : avoid using "optional" keyword (#4283) 2023-12-01 20:39:12 +02:00
Georgi Gerganov d5a1cbde60 llama : support optional tensors (#4283) 2023-12-01 20:35:47 +02:00
Georgi GerganovandGitHub 880f57973b llama : fix integer overflow during quantization (#4284) 
happens with multi-threaded quantization of Qwen-72B

ggml-ci
 2023-12-01 18:42:11 +02:00
Georgi GerganovandGitHub ef47ec18da ggml : add ggml_soft_max_ext (#4256) 
* metal : implement soft_max_ext

* cuda : implement soft_max_ext

* ggml : implement soft_max_ext (CPU)

* batched-bench : print threads

ggml-ci

* metal : simplify soft_max encoding

ggml-ci

* cuda : use 512 threads for soft_max instead of 32

* ggml : update soft max cpu

* cuda : do warp-based block reduce

* cuda : increase max block size to 1024

* cuda : fix warp reduction initialization of shared mem

* metal : warp-based reduction for soft max kernel

* metal : warp-based reduce for rms_norm

* metal : simplify soft max kernel

ggml-ci

* alloc : fix build with debug
 2023-12-01 10:51:24 +02:00
Georgi Gerganov 1f5cd83275 examples : add readme files 2023-11-29 11:00:17 +02:00
Georgi GerganovandGitHub 8406b0924b ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240) 
* ggml : use blas even if src0 is not F32

* llama : use n_threads_batch only when n_tokens >= 32

ggml-ci

* llama : revert n_threads_batch logic

ggml-ci
 2023-11-28 10:32:03 +02:00
Georgi Gerganov 3e73d31d9c lookahead : support -n -1 infinite generation 2023-11-26 21:52:23 +02:00
Georgi GerganovandGitHub 9656026b53 readme : update hot topics 2023-11-26 20:42:51 +02:00
Georgi GerganovGitHubslaren
 		922754a8d6 lookahead : add example for lookahead decoding (#4207) 
* lookahead : init

* lookahead : generate and store n-grams

* lookahead : use loop instead recursion to generate n-grams

* lookahead : initial working implementation

* lookahead : filter repeating n-grams

* lookahead : use deterministic init

* lookahead : add to Makefile

* lookahead : fix a bug in the seq_id of the lookahead tokens

* lookahead : add comments

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-11-26 20:33:07 +02:00
Georgi GerganovandGitHub 04814e718e readme : update hot topics 2023-11-25 12:02:13 +02:00
Georgi GerganovGitHubkir-gadjelloTobi Lütke
 		af19d35734 server : OAI API compatibility (#4198) 
* Add openai-compatible POST /v1/chat/completions API endpoint to server example

* fix code style

* Update server README.md

* Improve server README.md

* Fix server.cpp code style according to review

* server : some style changes

* server : indentation

* server : enable special tokens during tokenization by default

* server : minor code style

* server : change random string generator

* straightforward /v1/models endpoint

---------

Co-authored-by: kir-gadjello <111190790+kir-gadjello@users.noreply.github.com>
Co-authored-by: Tobi Lütke <tobi@Tobis-MacBook-Pro.local>
 2023-11-25 11:29:06 +02:00
Georgi GerganovGitHubKerfuffle
 		6b0a7420d0 llama : KV cache view API + better KV cache management (#4170) 
* llama : keep track of used KV cells + better KV cache management

* llama : zero KV cache used upon clear

ggml-ci

* llama : allow exporting a view of the KV cache (#4180)

* Allow exporting a view of the KV cache

* Allow dumping the sequences per cell in common

* Track max contiguous cells value and position as well

* Fix max contiguous empty cells index calculation

Make dump functions deal with lengths or sequences counts > 10 better

* Fix off by one error in dump_kv_cache_view

* Add doc comments for KV cache view functions

Eliminate cell sequence struct; use llama_seq_id directly

Minor cleanups

* common : add -dkvc arg for enabling kv cache dumps

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
 2023-11-23 19:07:56 +02:00
Georgi GerganovandGitHub d103d935c0 readme : update hot topics 2023-11-23 13:51:22 +02:00
Georgi Gerganov ff8238f71d docs : add llama-star arch idea 2023-11-23 11:35:04 +02:00
Georgi Gerganov dae06c06e5 Revert "finetune : add --n-gpu-layers flag info to --help (#4128)" 
This reverts commit 05e8301e45.
 2023-11-19 19:16:07 +02:00
Georgi Gerganov 35985acffa gitignore : tokenize 2023-11-19 18:50:49 +02:00
Georgi Gerganov 5ad387e994 tokenize : fix trailing whitespace 2023-11-17 18:01:38 +02:00
Georgi GerganovandGitHub 4f447a4833 llama : fix data units (#4101) 
* llama : fix data units

ggml-ci

* Revert "llama : fix data units"

This reverts commit f5feac831fe225ed7f3db938d115732a49dccfc4.

* llama : disambiguate data units

ggml-ci
 2023-11-17 10:00:15 +02:00
Georgi GerganovandGitHub 3d68f364f1 ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060) 
ggml-ci
 2023-11-13 16:55:52 +02:00
Georgi GerganovandGitHub c049b37d7b readme : update hot topics 2023-11-13 14:18:08 +02:00
Georgi GerganovandGitHub 4760e7cc0b sync : ggml (backend v2) (#3912) 
* sync : ggml (backend v2) (wip)

* sync : migrate examples and llama.cpp to dynamic graphs (wip)

* sync : update tests + fix max op params to 64

ggml-ci

* sync : ggml-cuda

ggml-ci

* llama : fix save/load state context size

ggml-ci

* sync : try to fix build on tvOS

* sync : pass custom graph sizes in training examples

* sync : update graph copies to new ggml API

* sync : update sync-ggml.sh with new files

* scripts : fix header in sync script

* train : fix context size calculations

* llama : increase inference graph size up to 4096 nodes

* train : allocate grads for backward graphs

* train : allocate grads for gb_tmp
 2023-11-13 14:16:23 +02:00
Georgi GerganovandGitHub 413503d4b9 make : do not add linker flags when compiling static llava lib (#3977) 2023-11-07 20:25:32 +03:00
Georgi Gerganov 8f961abdc4 speculative : change default p_accept to 0.5 + CLI args (#3919) 
ggml-ci
 2023-11-03 09:41:56 +02:00
Georgi GerganovandGitHub 05816027d6 common : YAYF (yet another YARN fix) (#3925) 
ggml-ci
 2023-11-03 09:24:00 +02:00
Georgi GerganovandGitHub 224e7d5b14 readme : add notice about #3912 2023-11-02 20:44:12 +02:00
Georgi GerganovandGitHub c7743fe1c1 cuda : fix const ptrs warning causing ROCm build issues (#3913) 2023-11-02 20:32:11 +02:00
Georgi GerganovandGitHub 4ff1046d75 gguf : print error for GGUFv1 files (#3908) 2023-11-02 16:22:30 +02:00
Georgi GerganovandGitHub 2756c4fbff gguf : remove special-case code for GGUFv1 (#3901) 
ggml-ci
 2023-11-02 11:20:21 +02:00
Georgi Gerganov 1efae9b7dc llm : prevent from 1-D tensors being GPU split (#3697) 2023-11-02 09:54:44 +02:00
Georgi GerganovandGitHub 4d719a6d4e cuda : check if this fixes Pascal card regression (#3882) 2023-11-02 08:35:10 +02:00
Georgi GerganovandGitHub 183b3fac6c metal : fix build errors and kernel sig after #2268 (#3898) 2023-11-02 08:33:37 +02:00
Georgi Gerganov c43c2da8af llm : fix llm_build_kqv taking unused tensor (benign, #3837) 2023-11-01 23:08:30 +02:00
Georgi Gerganov 523e49b111 llm : fix falcon norm after refactoring (#3837) 2023-11-01 23:00:50 +02:00
Georgi GerganovandGitHub e16b9fa4ba metal : multi-simd softmax (#3710) 
ggml-ci
 2023-11-01 21:25:00 +02:00
Georgi Gerganov ff8f9a88da common : minor (#3715) 2023-11-01 21:15:55 +02:00
Georgi GerganovandGitHub 50337961a6 llm : add llm_build_context (#3881) 
* llm : add llm_build_context

* llm : deduce norm eps based on type + explict max_alibi_bias, clamp_kqv

* llm : restore the non-graph llm_build_ functional API

ggml-ci

* llm : cleanup + comments
 2023-11-01 20:11:02 +02:00
Georgi Gerganov 9a3b4f6c86 ggml : fix UNUSED macro (#3762) 2023-11-01 13:50:45 +02:00
Georgi GerganovandGitHub 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
Georgi GerganovandGitHub 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
Georgi GerganovandGitHub 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
Georgi GerganovandGitHub 71a09da301 llama : fix kv shift bug (#3835) 
ggml-ci
 2023-10-29 18:32:51 +02:00
Georgi GerganovGitHubcebtenzzre
 		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
Georgi Gerganov ba231e8a6d issues : change label from bug to bug-unconfirmed (#3748) 2023-10-28 15:35:26 +03:00
Georgi GerganovandGitHub 8a2f2fea29 convert : ignore tokens if their IDs are within [0, vocab_size) (#3831) 2023-10-28 06:25:15 -06:00
Georgi GerganovandGitHub 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
Georgi GerganovandGitHub 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
Georgi GerganovandGitHub 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
Georgi Gerganov 34b2a5e1ee server : do not release slot on image input (#3798) 2023-10-26 22:54:17 +03:00
Georgi Gerganov 6961c4bd0b batched-bench : print params at start 2023-10-25 10:26:27 +03:00
Georgi Gerganov cc44877486 log : disable pid in log filenames 2023-10-25 10:09:16 +03:00
Georgi GerganovandGitHub 1717521cdb server : do not block system prompt update (#3767) 
* server : do not block system prompt update

* server : update state machine logic to process system prompts

* server : minor
 2023-10-24 23:08:20 +03:00
Georgi GerganovandGitHub b2f7e04bd3 sync : ggml (conv ops + cuda MSVC fixes) (#3765) 
ggml-ci
 2023-10-24 21:51:20 +03:00
Georgi GerganovGitHubKerfuffle
 		2b4ea35e56 cuda : add batched cuBLAS GEMM for faster attention (#3749) 
* cmake : add helper for faster CUDA builds

* batched : add NGL arg

* ggml : skip nops in compute_forward

* cuda : minor indentation

* cuda : batched cuBLAS GEMMs for src0 F16 and src1 F32 (attention ops)

* Apply suggestions from code review

These changes plus:

```c++
#define cublasGemmBatchedEx hipblasGemmBatchedEx
```

are needed to compile with ROCM. I haven't done performance testing, but it seems to work.

I couldn't figure out how to propose a change for lines outside what the pull changed, also this is the first time trying to create a multi-part review so please forgive me if I mess something up.

* cuda : add ROCm / hipBLAS cublasGemmBatchedEx define

* cuda : add cublasGemmStridedBatchedEx for non-broadcasted cases

* cuda : reduce mallocs in cublasGemmBatchedEx branch

* cuda : add TODO for calling cublas from kernel + using mem pool

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
 2023-10-24 16:48:37 +03:00
Georgi Gerganov 469c9addef metal : handle ggml_scale for n%4 != 0 (close #3754) 
ggml-ci
 2023-10-24 09:47:22 +03:00