root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-10 02:31:46 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Commit Graph

  • a979e71ddc add obj flags to all output make targets Concedo 2023-06-08 16:28:26 +0800
  • a5cd1955d6 !fixup Johannes 2023-06-08 10:25:09 +0200
  • 4a82c8d45c clang-tidy : add config back Iwan Kawrakow 2023-06-08 11:08:19 +0300
  • 85a9714316 Windows nvcc bug workaround Johannes 2023-06-08 10:02:37 +0200
  • 8fc8179919
         Add llama.cpp docker support for non-latin languages (#1673) qingfengfenga 2023-06-08 15:58:53 +0800
  • 85f902d5c4
         Merge 'origin/master' into hipblas Henri Vasserman 2023-06-08 10:50:28 +0300
  • 9eb9d14216 Merge remote-tracking branch 'origin/master' into ik/q6_k_metal Iwan Kawrakow 2023-06-08 10:41:29 +0300
  • 22d03847f5 Metal implementation for Q6_K Iwan Kawrakow 2023-06-08 10:09:52 +0300
  • b50b570ed9
         ggml : fix fprintf warnings (#1720) master-b50b570 Steven Roussey 2023-06-08 00:12:28 -0700
  • 53aba3f393
         clang-tidy : restore dot file from accidental deletion Georgi Gerganov 2023-06-08 10:09:08 +0300
  • 4161bdc04d
         metal : add Q4_K implementation (#1733) Kawrakow 2023-06-08 10:08:23 +0300
  • 0035858273
         k-quants : add missing compile definition to CMakeLists (#1748) master-0035858 johnson442 2023-06-08 08:02:48 +0100
  • a498987551 Add missing compile definition to CMakeLists for k_quants johnson442 2023-06-08 03:51:55 +0100
  • 6b7487d104
         store view offset and permute axes in opt[0] instead of storing it in padding xaedes 2023-06-08 02:33:57 +0200
  • 8cea3ab9e5 add examples for llava.py ningshanwutuobang 2023-06-08 04:50:31 +0800
  • 64a06536cb Merge remote-tracking branch 'upstream/master' Randall Fitzgerald 2023-06-07 12:23:49 -0400
  • 6635f7efce updated lite Concedo 2023-06-08 00:20:32 +0800
  • e2b059d335 fix fprintf warnings Steven Roussey 2023-06-07 08:44:50 -0700
  • 6ed4893391 fixed add end condition for generating ningshanwutuobang 2023-06-07 23:44:54 +0800
  • 49a6be3d87 add llama metal compile flags as an option Concedo 2023-06-07 22:29:38 +0800
  • b13fa0b9c6 Add opencl release memory edp1096 2023-06-07 22:50:43 +0900
  • 7b0707ff26 Merge branch 'master' into concedo_experimental Concedo 2023-06-07 17:06:56 +0800
  • e3c26e815d ggml : Load data into int8x16x4_t using vld4q_s8 on arm64 lindeer 2023-06-07 16:26:29 +0800
  • 5c64a0952e
         k-quants : allow to optionally disable at compile time (#1734) master-5c64a09 Georgi Gerganov 2023-06-07 10:59:52 +0300
  • 63f163f0dd
         build : enable k-quants by default Georgi Gerganov 2023-06-07 10:53:59 +0300
  • edaafec6cc
         k-quants : put behind optional compile flag LLAMA_K_QUANTS Georgi Gerganov 2023-06-07 10:14:15 +0300
  • e78c675a6e Merge branch 'master' into concedo_experimental Concedo 2023-06-07 15:23:29 +0800
  • 75ad0c0614 Fix after merge with master Iwan Kawrakow 2023-06-07 09:53:50 +0300
  • a5becf764b Optimizing q4_K metal dot some more Iwan Kawrakow 2023-06-07 09:16:01 +0300
  • 1e903f6b82 Optimizing Q4_K on metal Iwan Kawrakow 2023-06-06 20:07:37 +0300
  • 6f8f39fbaf Metal implementation for Q4_K Iwan Kawrakow 2023-06-06 17:42:28 +0300
  • 5b57a5b726
         flake : update to support metal on m1/m2 (#1724) jacobi petrucciani 2023-06-07 00:15:31 -0400
  • 4dc62c545d
         readme : add June roadmap Georgi Gerganov 2023-06-07 07:15:08 +0300
  • 92ee6a940b
         update flake to support metal on m1/m2 jacobi petrucciani 2023-06-06 23:13:23 -0400
  • 35a84916fb
         main: add the possibility to open the prompt cache read-only (#1640) master-35a8491 Willy Tarreau 2023-06-07 04:10:17 +0200
  • 40ed39d7a7 Modify Dockerfile default character set to improve compatibility (#1673) qingfengfenga 2023-06-07 09:59:18 +0800
  • 994ebe1218
         Merge branch 'ggerganov:master' into master qingfengfenga 2023-06-07 09:51:20 +0800
  • 4362e805a4
         Merge 'origin/master' into hipblas Henri Vasserman 2023-06-06 23:14:40 +0300
  • 2d7bf110ed
         llama : fix vram_scratch var master-2d7bf11 Georgi Gerganov 2023-06-06 22:54:39 +0300
  • 2a4e41a086
         llama : fix compile warnings Georgi Gerganov 2023-06-06 22:41:53 +0300
  • 17366df842
         Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703) master-17366df Johannes Gäßler 2023-06-06 21:33:23 +0200
  • fa221a27cc fixup! CUDA multi GPU + scratch JohannesGaessler 2023-06-06 21:05:54 +0200
  • 8c6c3347cc docker: add support for CUDA in docker canardleteer 2023-05-14 17:36:14 -0700
  • 0f7f3f174d CUDA multi GPU + scratch JohannesGaessler 2023-05-23 09:17:31 +0200
  • 44f906e853
         metal : add f16 support master-44f906e Georgi Gerganov 2023-06-06 20:16:57 +0300
  • d5b111f53d
         Clblast fixes + enhancements to save VRAM and offload more layers (#1675) master-d5b111f LostRuins 2023-06-07 01:00:01 +0800
  • b6dd367b45
         Update ggml-opencl.cpp 0cc4m 2023-06-06 17:55:41 +0200
  • fa5b3d7365
         fix makefile. Henri Vasserman 2023-06-06 18:47:00 +0300
  • 1ba4ce4ad7
         Revert "warp size fixes" Henri Vasserman 2023-06-06 18:41:08 +0300
  • 5d6eb72164
         warp size fixes Henri Vasserman 2023-06-06 18:32:41 +0300
  • ed603dcafc Merge branch 'master' into concedo_experimental Concedo 2023-06-06 23:12:01 +0800
  • ba1f617d7d add free for context ningshanwutuobang 2023-06-06 22:57:04 +0800
  • c046db5197 lite bugfixes, buffer size changes, fixed a topk bug. Concedo 2023-06-06 22:38:25 +0800
  • 9c6117cd8d fixed sampling ningshanwutuobang 2023-06-06 22:29:34 +0800
  • a91487093b add test example for embd input ningshanwutuobang 2023-06-06 22:06:51 +0800
  • 33091a9bd3
         Merge 'origin/master' into hipblas Henri Vasserman 2023-06-06 16:19:23 +0300
  • 2d43387daf
         ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710) master-2d43387 Georgi Gerganov 2023-06-06 10:18:03 +0300
  • 7ad7750c5c
         gitignore : add .clang-tidy Georgi Gerganov 2023-06-06 09:55:10 +0300
  • 7a74dee6b4
         llama : temporary disable Q6_K output quantization (#1711) master-7a74dee Georgi Gerganov 2023-06-06 09:39:38 +0300
  • d5b60af230 Makefile: add missing ggml-quants-k.o to server target Efruit 2023-06-06 01:27:15 -0400
  • 590250f7a9
         metal : add checks for buffer size (#1706) master-590250f Spencer Sutton 2023-06-05 23:28:17 -0400
  • 8dd5b0854f disable tty Spencer Kim 2023-06-05 18:00:26 -0700
  • 827fd74b02 Add checks for buffer size on metal Spencer Sutton 2023-06-05 17:31:51 -0400
  • b3d605dc75 Use std::runtime_error exceptions. KerfuffleV2 2023-06-05 14:33:53 -0600
  • 7ed5aca9ca Clean up thread blocks with spares calculation a bit KerfuffleV2 2023-06-05 13:36:35 -0600
  • fe9ed7d36f Threaded dequantizing and f16 to f32 conversion KerfuffleV2 2023-06-05 13:18:55 -0600
  • 5c7b0e79a7 Add support for quantizing already quantized models KerfuffleV2 2023-06-04 11:33:18 -0600
  • f4c55d3bd7
         docs : add performance troubleshoot + example benchmark documentation (#1674) Yuval Peled 2023-06-05 23:32:36 +0300
  • 3970f417b5
         Merge branch 'master' into master Georgi Gerganov 2023-06-05 23:32:06 +0300
  • f1465624c2
         readme : fix typo (#1700) Foul-Tarnished 2023-06-05 22:28:37 +0200
  • c2df36d60d
         llama : consistently catch and throw only exceptions deriving from std::exception (#1599) master-c2df36d mgroeber9110 2023-06-05 22:24:29 +0200
  • 9d0693bce3
         metal : use shared buffers between CPU and GPU (#1696) master-9d0693b kiltyj 2023-06-05 13:24:04 -0700
  • e129f0bd76
         metal : remove unnecessary copies Georgi Gerganov 2023-06-05 23:23:00 +0300
  • efe0507632
         ggml : fix internal overflow in ggml_time_us on Windows (#1702) master-efe0507 grahameth 2023-06-05 22:11:49 +0200
  • 719962fc4f
         Merge branch 'master' into catch_std_exception Georgi Gerganov 2023-06-05 23:11:32 +0300
  • e7fe66e670
         ci : disable auto tidy (#1705) master-e7fe66e Georgi Gerganov 2023-06-05 23:05:05 +0300
  • fee3f7ed0a
         ci : disable auto tidy Georgi Gerganov 2023-06-05 23:03:33 +0300
  • 99009e72f8
         ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684) master-99009e7 Kawrakow 2023-06-05 22:56:18 +0300
  • af275faece
         Merge branch 'master' into ik/k_quants Georgi Gerganov 2023-06-05 22:54:21 +0300
  • 12d43443b2
         ggml : rename k_quants -> ggml-quants-k, use lowercase in code Georgi Gerganov 2023-06-05 22:53:07 +0300
  • c79da27ac7 Merge branch 'master' into catch_std_exception mgroeber9110 2023-06-05 21:34:40 +0200
  • c38b0bbf82 Only import unistd.h for Metal builds Kilty McGowan 2023-06-05 09:02:14 -0700
  • 2e5edc80e0 updated lite Concedo 2023-06-05 23:56:24 +0800
  • 79df932d0a added dropdown for blasbatch. added capability to build avx clblast but not in default build for now Concedo 2023-06-05 22:50:21 +0800
  • 9caca8d11f ggml: Fix internal overflow in ggml_time_us on Windows grahameth 2023-06-05 16:43:22 +0200
  • 20d5eef816 add examples of input floats ningshanwutuobang 2023-06-05 22:32:36 +0800
  • a379e40ba9
         Update Makefile DaniAndTheWeb 2023-06-05 15:56:10 +0200
  • 5673a8de37 fixed inpL shape and type ningshanwutuobang 2023-06-05 21:39:35 +0800
  • 11af67866e Fixed single GPU performance regression JohannesGaessler 2023-06-05 14:32:20 +0200
  • 9cec6a5ff0
         fix small typo in README.md Foul-Tarnished 2023-06-05 14:15:58 +0200
  • c1b44240d7 Remove trailing whitespace Kilty McGowan 2023-06-05 05:02:38 -0700
  • 5220a991a5
         Increase 3B scratch buffers. (#1698) master-5220a99 Henri Vasserman 2023-06-05 13:43:08 +0300
  • 1855e0820e removed jni files (moved them to caller android project) George 2023-06-05 17:54:57 +0800
  • c3b4efc89e updated CMakeLists.txt and added JNI implementation to support building this library as a dependency in Android Studio with NDK George 2023-06-05 17:25:51 +0800
  • dffd2a710d
         Increase 3B scratch buffers. Henri Vasserman 2023-06-05 12:08:04 +0300
  • d1f563a743
         llama : fix Metal KV cache sync (close #1695) master-d1f563a Georgi Gerganov 2023-06-05 10:19:03 +0300
  • a9d0bea047 Page-align buffers used by Metal Kilty McGowan 2023-06-04 23:16:45 -0700
  • 54dc75ce73 Merge branch 'concedo-opencl-dev' into concedo_experimental Concedo 2023-06-05 13:31:53 +0800
  • f6431ded5d removed flags from the CL pool malloc, apply code tidying suggestions. Concedo 2023-06-05 13:31:37 +0800
  • c27f250b6f bigger scratch buffer for 3B llama Concedo 2023-06-05 13:24:53 +0800