nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity
5,392 Commits 1 Branch 0 Tags
c753d7bed0dc2cc2d5c42dfa9806cba91748392e
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Johannes GäßlerandGitHub 4696d56749 CUDA: fix crash on large batch size for quant. MoE (#13537) 2025-05-14 16:41:02 +02:00
Johannes GäßlerandGitHub 6da34fa276 CUDA: faster Deepseek FA, add Turing support (#13435) 2025-05-14 16:08:20 +02:00
Johannes GäßlerandGitHub 10d2af0eaa llama/ggml: add LLM training support (#10544) 
* llama/ggml: add LLM training support

more compact progress bar

llama_save_model_to_file

llama_opt_param_filter

ggml_graph_dup force_grads

refactor ggml_opt, fix test-opt

* remove logits_all

* refactor CUDA implementation for ACC

* reset graph at beginning of opt period
 2025-05-12 14:44:49 +02:00
Johannes GäßlerandGitHub 95e18884fc CUDA: fix misaligned synchronization in FA (#13469) 2025-05-12 10:51:21 +02:00
Johannes GäßlerandGitHub 7474e00b34 CUDA: fix crash with partial offloading of MoE (#13439) 2025-05-11 16:09:33 +02:00
Johannes GäßlerandGitHub 0208355f42 CUDA: fix race conditions FlashAttention kernels (#13438) 2025-05-10 22:22:48 +02:00
Johannes GäßlerandGitHub d8919424f1 CUDA: fix FlashAttention on Turing (#13415) 2025-05-10 09:16:52 +02:00
Johannes GäßlerandGitHub 0cf6725e9f CUDA: FA support for Deepseek (Ampere or newer) (#13306) 
* CUDA: FA support for Deepseek (Ampere or newer)

* do loop unrolling via C++ template
 2025-05-09 13:34:58 +02:00
Johannes GäßlerandGitHub 5c86c9ed3e CUDA: fix crash on large batch size for MoE models (#13384) 2025-05-09 12:14:04 +02:00
Johannes GäßlerandGitHub 141a908a59 CUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF (#13135) 2025-05-06 23:35:51 +02:00
Johannes GäßlerandGitHub 2356fb1d53 CUDA: fix bad asserts for partial offload (#13337) 2025-05-06 13:58:51 +02:00
Johannes GäßlerandGitHub 15a28ec8c7 CUDA: fix --split-mode row for MMQ (#13323) 2025-05-06 08:36:46 +02:00
Johannes GäßlerandGitHub 9070365020 CUDA: fix logic for clearing padding with -ngl 0 (#13320) 2025-05-05 22:32:13 +02:00
Johannes GäßlerandGitHub 93c4e23905 CUDA: fix race condition in MMQ stream-k fixup (#13299) 2025-05-04 14:16:39 +02:00
Johannes GäßlerandGitHub 8afbd96818 CUDA: fix race condition in MMQ ids_dst (#13294) 2025-05-04 13:58:38 +02:00
Johannes GäßlerandGitHub 3e959f0976 imatrix: fix oob writes if src1 is not contiguous (#13286) 2025-05-04 00:50:37 +02:00
Johannes GäßlerandGitHub b0ecbd434b test: non-cont. b in test-backend-ops -o MUL_MAT (#13187) 2025-05-01 20:18:56 +02:00
Johannes GäßlerandGitHub e1e8e0991f CUDA: batched+noncont MMQ, refactor bs>1 MoE code (#13199) 2025-04-30 23:12:59 +02:00
Johannes GäßlerandGitHub 19e899ce21 scripts: n_depth for compare-llama-bench [no ci] (#13201) 2025-04-29 23:32:04 +02:00
Johannes GäßlerandGitHub cdf76586b2 CUDA: fix non-cont. inputs for batched mat mul (#13155) 2025-04-29 16:00:27 +02:00
Johannes GäßlerandGitHub 69699be48a CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (#13137) 2025-04-28 09:29:26 +02:00
Johannes GäßlerandGitHub b10d8bfdb1 CUDA: use switch statements in constexpr functions (#13095) 2025-04-24 15:57:10 +02:00
Johannes GäßlerandGitHub 658987cfc9 CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014) 
* CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID

* fix logic for RoPE support, CUDA graphs
 2025-04-22 21:27:40 +02:00
Johannes GäßlerandGitHub dd373dd3bf llama: fix error on bad grammar (#12628) 2025-03-28 18:08:52 +01:00
Johannes GäßlerandGitHub 5220a16d18 CUDA: fix FA logic for PTX 7.0 and CC >= 7.5 (#12222) 2025-03-06 18:45:09 +01:00
Johannes GäßlerandGitHub 9c42b1718c CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098) 2025-02-28 09:26:43 +01:00
Johannes GäßlerandGitHub a28e0d5eb1 CUDA: app option to compile without FlashAttention (#12025) 2025-02-22 20:44:34 +01:00
Johannes GäßlerandGitHub 5fa07c2f93 CUDA: optimize FA for GQA + large batches (#12014) 2025-02-22 12:20:17 +01:00
Johannes GäßlerandGitHub 586d5fe6eb doc: update contributing guidelines [no ci] (#11969) 2025-02-21 12:51:25 +01:00
Johannes GäßlerandGitHub d04e7163c8 doc: add links to ggml examples [no ci] (#11958) 2025-02-19 20:45:17 +01:00
Johannes GäßlerGitHubDiego Devesa
 		73e2ed3ce3 CUDA: use async data loading for FlashAttention (#11894) 
* CUDA: use async data loading for FlashAttention

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2025-02-17 14:03:24 +01:00
Johannes GäßlerandGitHub 6dde178248 scripts: fix compare-llama-bench commit hash logic (#11891) 2025-02-15 20:23:22 +01:00
Johannes GäßlerandGitHub c3d6af7cd2 CUDA: fix CUDART_VERSION checks (#11821) 2025-02-12 13:16:39 +01:00
Johannes GäßlerGitHubDiego Devesa
 		b9ab0a4d0b CUDA: use arch list for compatibility check (#11775) 
* CUDA: use arch list for feature availability check

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2025-02-11 00:17:22 +01:00
Johannes GäßlerandGitHub d80be897ac CUDA: fix min. version for movmatrix (#11751) 2025-02-08 10:46:07 +01:00
Johannes GäßlerandGitHub fa62da9b2d CUDA: support for mat. mul. with ne03 != ne13 (#11656) 2025-02-05 08:58:31 +01:00
Johannes GäßlerGitHubGeorgi Gerganov
 		fd08255d0d CUDA: non-contiguous (RMS) norm support (#11659) 
* CUDA: non-contiguous (RMS) norm support

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-02-04 22:21:42 +01:00
Johannes GäßlerandGitHub 21c84b5d2d CUDA: fix Volta FlashAttention logic (#11615) 2025-02-03 14:25:56 +02:00
Johannes GäßlerandGitHub 6eecde3cc8 HIP: fix flash_attn_stream_k_fixup warning (#11604) 2025-02-02 23:48:29 +01:00
Johannes GäßlerGitHubDiego Devesa
 		864a0b67a6 CUDA: use mma PTX instructions for FlashAttention (#11583) 
* CUDA: use mma PTX instructions for FlashAttention

* __shfl_sync workaround for movmatrix

* add __shfl_sync to HIP

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2025-02-02 19:31:09 +01:00
Johannes GäßlerandGitHub df984e0147 llama: refactor llama_decode_impl (#11381) 2025-01-27 12:07:12 +01:00
Johannes GäßlerandGitHub c5d9effb49 CUDA: fix FP16 cuBLAS GEMM (#11396) 2025-01-24 21:02:43 +01:00
Johannes GäßlerandGitHub 8137b4bb2b CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380) 2025-01-24 12:38:31 +01:00
Johannes GäßlerandGitHub 9c8dcefe17 CUDA: backwards pass for misc. ops, add tests (#11257) 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
 2025-01-16 16:43:38 +01:00
Johannes GäßlerandGitHub 432df2d5f9 RoPE: fix back, CUDA support for back + noncont. (#11240) 
* RoPE: fix back, CUDA support for back + noncont.

* fix comments reg. non-cont. RoPE support [no-ci]
 2025-01-15 12:51:37 +01:00
Johannes GäßlerandGitHub 53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030) 
* 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
 2025-01-07 18:01:58 +01:00
Johannes GäßlerandGitHub 46e3556e01 CUDA: add BF16 support (#11093) 
* CUDA: add BF16 support
 2025-01-06 02:33:52 +01:00
Johannes GäßlerandGitHub cd920d0ac3 tests: disable GGUF test for bad value size (#10886) 2024-12-19 08:53:58 +01:00
Johannes GäßlerandGitHub 081b29bd2a tests: add tests for GGUF (#10830) 2024-12-17 19:09:35 +01:00
Johannes GäßlerandGitHub 26a8406ba9 CUDA: fix shared memory access condition for mmv (#10740) 2024-12-09 20:07:12 +01:00
Johannes GäßlerandGitHub 890719311b common: fix warning message when no GPU found (#10564) 2024-11-28 18:15:25 +01:00
Johannes GäßlerandGitHub 1f922254f0 Github: update issue templates [no ci] (#10489) 2024-11-25 19:18:37 +01:00
Johannes GäßlerandGitHub 599b3e0cd4 GitHub: ask for more info in issue templates (#10426) 
* GitHub: ask for more info in issues [no ci]

* refactor issue templates to be component-specific

* more understandable issue description

* add dropdown for llama.cpp module
 2024-11-22 08:32:40 +01:00
Johannes GäßlerandGeorgi Gerganov 02e4eaf22f ggml-opt: fix data corruption (ggml/1022) 2024-11-21 09:22:02 +02:00
Johannes GäßlerandGitHub 75207b3a88 docker: use GGML_NATIVE=OFF (#10368) 2024-11-18 00:21:53 +01:00
Johannes GäßlerandGitHub 76e9e58b78 CUDA: fix MMV kernel being used for FP16 src1 (#10357) 2024-11-17 23:20:42 +01:00
Johannes GäßlerandGitHub ce2e59ba10 CMake: fix typo in comment [no ci] (#10360) 2024-11-17 12:59:38 +01:00
Johannes GäßlerandGitHub c3ea58aca4 CUDA: remove DMMV, consolidate F16 mult mat vec (#10318) 2024-11-17 09:09:55 +01:00
Johannes GäßlerandGitHub 467576b6cc CMake: default to -arch=native for CUDA build (#10320) 2024-11-17 09:06:34 +01:00
Johannes GäßlerandGeorgi Gerganov 8a43e940ab ggml: new optimization interface (ggml/988) 2024-11-17 08:30:29 +02:00
Johannes GäßlerandGitHub 4e54be0ec6 llama/ex: remove --logdir argument (#10339) 2024-11-16 23:00:41 +01:00
Johannes GäßlerandGitHub 4047be74da scripts: update compare-llama-bench.py (#10319) 2024-11-15 21:19:03 +01:00
Johannes GäßlerandGitHub 4a8ccb37ad CUDA: no -sm row for very small matrices (#10185) 2024-11-14 13:00:15 +01:00
Johannes GäßlerandGitHub 167a515651 CUDA: fix insufficient buffer clearing for MMQ (#10032) 2024-10-24 14:40:23 +02:00
Johannes GäßlerandGitHub c39665f589 CUDA: fix MMQ for non-contiguous src0, add tests (#10021) 
* CUDA: fix MMQ for non-contiguous src0, add tests

* revise test code
 2024-10-24 11:09:36 +02:00
Johannes GäßlerandGeorgi Gerganov 80273a306d CUDA: fix 1D im2col, add tests (ggml/993) 2024-10-23 16:50:02 +03:00
Johannes GäßlerandGeorgi Gerganov fabdc3bda3 ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980) 2024-10-03 21:17:26 +03:00
Johannes GäßlerandGeorgi Gerganov eee39bdc96 ggml: refactor cross entropy loss CPU impl. (ggml/976) 2024-10-03 21:17:26 +03:00
Johannes GäßlerandGeorgi Gerganov e98c1c188e test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974) 2024-10-01 16:07:40 +03:00
Johannes GäßlerandGeorgi Gerganov 7254cdf7e8 ggml: fix gradient allocation logic (ggml/966) 
* ggml: fix gradient allocation logic

* gradient allocation in ggml_build_backward_expand

* fixup

* fix test-backend-ops grad

* suggestions by slaren

* fix test1.c

* fix legacy opt API

* fix test-grad0

* remove keep arg
 2024-10-01 16:07:38 +03:00
Johannes GäßlerandGeorgi Gerganov aaa4099925 CUDA: remove bad assert (ggml/972) 2024-09-29 21:15:37 +03:00
Johannes GäßlerandGitHub a5b57b08ce CUDA: enable Gemma FA for HIP/Pascal (#9581) 2024-09-22 09:34:52 +02:00
Johannes GäßlerGeorgi Gerganovslaren
 		424c5d00a9 ggml/examples: add backend support for numerical optimization (ggml/949) 
* CUDA eval works

* stochastic gradient descent op

* Adam except decay

* CUDA CROSS_ENTROPY_LOSS_BACK

* CUDA mnist-fc training works

* backend CLI arg

* refactor gguf load

* remove sched from opt_step_adam

* implement l1 regularization (weight decay)

* extra call to add optimizer

* initialize gradients with ggml_graph_reset

* gradient accumulation

* increment iter per eval instead of epoch

* adjust backend interfaces

* fix ggml_graph_reset without backend

* fix ggml graph export/import

* fixup

* rename

* revert ggml_opt changes

* more general CUDA repeat_back

* update documentation, fix CNN

* validation split

* add clarifying comment

* optimize PyTorch training

* adjust buffer size, thread count

* fix 0.0f validation split

* Update examples/mnist/mnist-common.cpp

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

* fix gradient accumulation

* tensor flag for accumulators -> tensor hash set

* Update include/ggml.h

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

* Update tests/test-backend-ops.cpp

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

* Update tests/test-backend-ops.cpp

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

* fix test prints

* Update src/ggml-backend.c

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

* better CUDA support for noncontiguous out_prod

* add comment

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
 2024-09-20 21:15:05 +03:00
Johannes GäßlerandGitHub 5cb12f6839 CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562) 2024-09-20 18:35:35 +02:00
Johannes GäßlerandGitHub 5af118efda CUDA: fix --split-mode row race condition (#9413) 2024-09-11 10:22:40 +02:00
Johannes GäßlerandGitHub 8e6e2fbe14 CUDA: fix variable name conflict for Windows build (#9382) 2024-09-09 14:22:53 +02:00
Johannes GäßlerandGeorgi Gerganov 202084d31d tests: add gradient tests for all backends (ggml/932) 
* tests: add gradient checking to test-backend-ops

* remove old comment

* reorder includes

* adjust SIN/COS parameters

* add documentation, use supports_op if possible
 2024-09-08 11:05:55 +03:00
Johannes GäßlerandGeorgi Gerganov dbbebcab33 ggml: fix ggml_graph_cpy undefined behavior (ggml/943) 2024-09-08 11:05:55 +03:00
Johannes GäßlerandGitHub f91fc5639b CUDA: fix Gemma 2 numerical issues for FA (#9166) 2024-08-25 22:11:48 +02:00
Johannes GäßlerandGitHub e11bd856d5 CPU/CUDA: Gemma 2 FlashAttention support (#8542) 
* CPU/CUDA: Gemma 2 FlashAttention support

* apply logit_softcap to scale in kernel

* disable logit softcapping tests on Metal

* remove metal check
 2024-08-24 21:34:59 +02:00
Johannes GäßlerandGitHub a8dbc6f753 CUDA/HIP: fix tests/test-backend-ops (#8896) 2024-08-07 09:07:52 +02:00
Johannes GäßlerandGitHub 641f5dd2a6 CUDA: fix padding logic for FP16/FP32 (#8884) 2024-08-06 17:13:55 +02:00
Johannes GäßlerandGitHub 6eeaeba126 cmake: use 1 more thread for non-ggml in CI (#8740) 2024-07-28 22:32:44 +02:00
Johannes GäßlerandGitHub 69c487f4ed CUDA: MMQ code deduplication + iquant support (#8495) 
* CUDA: MMQ code deduplication + iquant support

* 1 less parallel job for CI build
 2024-07-20 22:25:26 +02:00
Johannes GäßlerandGitHub a15ef8f8a0 CUDA: fix partial offloading for ne0 % 256 != 0 (#8572) 2024-07-18 23:48:47 +02:00
Johannes GäßlerandGitHub e02b597be3 lookup: fibonacci hashing, fix crashes (#8548) 2024-07-17 23:35:44 +02:00
Johannes GäßlerandGitHub 5e116e8dd5 make/cmake: add missing force MMQ/cuBLAS for HIP (#8515) 2024-07-16 21:20:59 +02:00
Johannes GäßlerandGitHub 808aba3916 CUDA: optimize and refactor MMQ (#8416) 
* CUDA: optimize and refactor MMQ

* explicit q8_1 memory layouts, add documentation
 2024-07-11 16:47:47 +02:00
Johannes GäßlerandGitHub a03e8dd99d make/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392) 2024-07-09 17:11:07 +02:00
Johannes GäßlerandGitHub 8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278) 2024-07-05 09:06:31 +02:00
Johannes GäßlerandGitHub bcefa03bc0 CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311) 2024-07-05 09:05:34 +02:00
Johannes GäßlerandGitHub cb5fad4c6c CUDA: refactor and optimize IQ MMVQ (#8215) 
* CUDA: refactor and optimize IQ MMVQ

* uint -> uint32_t

* __dp4a -> ggml_cuda_dp4a

* remove MIN_CC_DP4A checks

* change default

* try CI fix
 2024-07-01 20:39:06 +02:00
Johannes GäßlerandGitHub 85a267daaa CUDA: fix MMQ stream-k for --split-mode row (#8167) 2024-06-27 16:26:05 +02:00
Johannes GäßlerandGitHub c8771ab5f8 CUDA: fix misaligned shared memory read (#8123) 2024-06-26 08:28:02 +02:00
Johannes GäßlerandGitHub 2df373ac40 CUDA: fix matrix multiplication algorithm choice (#8102) 2024-06-25 01:22:33 +02:00
Johannes GäßlerandGitHub 3b099bcd9c CUDA: fix MMQ writeback for int8 tensor cores (#8100) 2024-06-24 22:15:33 +02:00
Johannes GäßlerandGitHub a818f3028d CUDA: use MMQ instead of cuBLAS by default (#8075) 2024-06-24 17:43:42 +02:00
Johannes GäßlerandGitHub 9a590c8226 CUDA: optimize MMQ int8 tensor core performance (#8062) 
* CUDA: optimize MMQ int8 tensor core performance

* only a single get_mma_tile_x_k function

* simplify code, make functions constexpr
 2024-06-24 12:41:23 +02:00
Johannes GäßlerGitHubslaren
 		abd894ad96 common: fix warning (#8036) 
* common: fix warning

* Update common/common.cpp

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

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-06-20 16:40:13 +02:00
Johannes GäßlerandGitHub d50f8897a7 CUDA: stream-k decomposition for MMQ (#8018) 
* CUDA: stream-k decomposition for MMQ

* fix undefined memory reads for small matrices
 2024-06-20 14:39:21 +02:00