4375 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Chenguang Li	7066b4cce2	CANN: RoPE and CANCAT operator optimization (#10488) ... Co-authored-by: noemotiovon <noemotiovon@gmail.com>	2024-11-26 17:31:05 +08:00
Junil Kim	0eb4e12bee	vulkan: Fix a vulkan-shaders-gen arugment parsing error (#10484) ... The vulkan-shaders-gen was not parsing the --no-clean argument correctly. Because the previous code was parsing the arguments which have a value only and the --no-clean argument does not have a value, it was not being parsed correctly. This commit can now correctly parse arguments that don't have values.	2024-11-26 01:47:20 +00:00
Eric Curtin	0cc63754b8	Introduce llama-run (#10291) ... It's like simple-chat but it uses smart pointers to avoid manual memory cleanups. Less memory leaks in the code now. Avoid printing multiple dots. Split code into smaller functions. Uses no exception handling. Signed-off-by: Eric Curtin <ecurtin@redhat.com>	2024-11-25 22:56:24 +01:00
Diego Devesa	50d5cecbda	ci : build docker images only once daily (#10503)	2024-11-25 22:05:39 +01:00
Georgi Gerganov	9fd8c2687f	server : add more information about error (#10455)	2024-11-25 22:28:59 +02:00
Georgi Gerganov	47f931c8f9	server : enable cache_prompt by default (#10501) ... ggml-ci	2024-11-25 21:50:07 +02:00
Georgi Gerganov	106964e3d2	metal : enable mat-vec kernels for bs <= 4 (#10491)	2024-11-25 21:49:31 +02:00
Shane A	80acb7b430	Rename Olmo1124 to Olmo2 (#10500)	2024-11-25 19:36:09 +01:00
Diego Devesa	10bce0450f	llama : accept a list of devices to use to offload a model (#10497) ... * llama : accept a list of devices to use to offload a model * accept `--dev none` to completely disable offloading * fix dev list with dl backends * rename env parameter to LLAMA_ARG_DEVICE for consistency	2024-11-25 19:30:06 +01:00
Johannes Gäßler	1f922254f0	Github: update issue templates [no ci] (#10489)	2024-11-25 19:18:37 +01:00
brucepro	a9a678a6b2	Add download chat feature to server chat (#10481) ... * Add download chat feature to server chat Add a download feature next to the delete chat feature in the server vue chat interface. * code style --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>	2024-11-25 17:11:55 +01:00
Georgi Gerganov	9ca2e67762	server : add speculative decoding support (#10455) ... * server : add speculative decoding support ggml-ci * server : add helper function slot.can_speculate() ggml-ci	2024-11-25 16:31:38 +02:00
Diego Devesa	5931c1f233	ggml : add support for dynamic loading of backends (#10469) ... * ggml : add support for dynamic loading of backends --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-11-25 15:13:39 +01:00
Georgi Gerganov	f6d12e7df8	tests : fix compile warning	2024-11-25 15:17:32 +02:00
Georgi Gerganov	b756441104	metal : minor code formatting	2024-11-25 15:08:04 +02:00
Neo Zhang Jianyu	5a8987793f	[SYCL] Fix building Win package for oneAPI 2025.0 update (#10483) ... * fix build package for 2025.0 * debug * debug * fix * rm debug --------- Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>	2024-11-25 17:31:10 +08:00
Georgi Gerganov	d9d54e498d	speculative : refactor and add a simpler example (#10362) ... * speculative : refactor and add a simpler example ggml-ci * speculative : clean-up and add comments and TODOs [no ci] * speculative : manage context in common_speculative ggml-ci * speculative : simplify ggml-ci * speculative : simplify (cont) ggml-ci * speculative : add --draft-min CLI arg * speculative : minor fixup * make : build fixes * speculative : do not redraft previous drafts ggml-ci * speculative : fix the draft sampling ggml-ci * speculative : fix compile warning * common : refactor args ggml-ci * common : change defaults [no ci] * common : final touches ggml-ci	2024-11-25 09:58:41 +02:00
Georgi Gerganov	cce5a90075	flake.lock: Update (#10470) ... Flake lock file updates: • Updated input 'nixpkgs': 'github:NixOS/nixpkgs/5e4fbfb6b3de1aa2872b76d49fafc942626e2add?narHash=sha256-OZiZ3m8SCMfh3B6bfGC/Bm4x3qc1m2SVEAlkV6iY7Yg%3D' (2024-11-15) → 'github:NixOS/nixpkgs/23e89b7da85c3640bbc2173fe04f4bd114342367?narHash=sha256-y/MEyuJ5oBWrWAic/14LaIr/u5E0wRVzyYsouYY3W6w%3D' (2024-11-19) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-11-24 08:03:25 -08:00
Diego Devesa	dc39012cba	llama : fix op mul check with command-r-plus (#10476)	2024-11-24 16:10:26 +01:00
Gabe Goodhart	9336db462c	convert : XLMRoberta Type Vocab Size (#10458) ... This matches the key in common bert-based embedding models and may have a value other than 1 in it. Branch: XLMRobertaTypeVocabSize Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>	2024-11-24 11:02:34 +02:00
momonga	96fa2c5e2d	fix gguf-py: Conversion error when multiple licenses are configured (#9807) ... * fix general.license list to str * fix join license list --------- Co-authored-by: momonga <115213907+mmnga@users.noreply.github.com>	2024-11-24 01:09:22 +01:00
Diego Devesa	55ed008b2d	ggml : do not use ARM features not included in the build (#10457)	2024-11-23 14:41:12 +01:00
蕭澧邦	6dfcfef078	ci: Update oneAPI runtime dll packaging (#10428) ... This is the minimum runtime dll dependencies for oneAPI 2025.0	2024-11-22 10:44:08 +01:00
Johannes Gäßler	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
leo-pony	c18610b4ee	CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216) ... * CANN Support Ascend310P to accelerate F32 and F16 Model * Add compile option soc type macro ASCEND_310P to ggml-cann lib * Remove unused code * Remove the ascend soc_type hard code compile option in CMakelist.txt	2024-11-22 14:07:20 +08:00
Diego Devesa	a5e47592b6	cuda : optimize argmax (#10441) ... * cuda : optimize argmax * remove unused parameter ggml-ci * fixup : use full warps ggml-ci * Apply suggestions from code review Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * fix ub * ggml : check ne00 <= INT32_MAX in argmax and argsort --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>	2024-11-21 18:18:50 +01:00
Georgi Gerganov	1bb30bf28c	llama : handle KV shift for recurrent models (#10402) ... ggml-ci	2024-11-21 10:22:47 +02:00
Georgi Gerganov	87a533be57	sync : ggml	2024-11-21 09:22:11 +02:00
slaren	59b9172822	ggml/sched : do not skip views in pre-assignments	2024-11-21 09:22:05 +02:00
Johannes Gäßler	02e4eaf22f	ggml-opt: fix data corruption (ggml/1022)	2024-11-21 09:22:02 +02:00
Jeff Bolz	9abe9eeae9	vulkan: predicate max operation in soft_max shaders/soft_max (#10437) ... Fixes #10434	2024-11-20 20:47:36 +01:00
bandoti	f95caa7954	cmake: add link dependencies to cmake find pkg (#10433) ... * cmake pkg: find accelerate, openmp, memkind libs * cmake pkg: find BLAS libs * try BLAS_LIBRARIES instead * Add BLAS link opts * Add more link deps. and set GGML_ vars	2024-11-20 17:22:19 +01:00
Diego Devesa	fab5d30ff6	llama : add .clang-format file (#10415)	2024-11-20 12:57:53 +01:00
Jeff Bolz	8fd4b7fa29	vulkan: copy iq4_nl LUT into shared memory (#10409)	2024-11-20 08:40:18 +01:00
Jeff Bolz	1bacb9f625	vulkan: further optimize mul_mat_vec using larger loads (#10387) ... * vulkan: Use pipeline_robustness to disable robustness in mul_mat_vec. Add some early returns for nonexistent rows in mul_mat_vec shaders. These can only be hit when dispatching a 2D grid of workgroups. Fix the logic for the 2D grid of workgroups to round up. Enable the pipeline robustness extension if it's available, and use it to disable robustness for these pipelines. The instructions to do the bounds checking contend for the same ALU resources as the bit twiddling dequant instructions. * vulkan: Add GLSL structure aliases for quant types to allow larger loads In Vulkan it's not possible to cast pointer types, so instead you have to declare an aliased binding for the memory with a different type. This commit adds aliases for the quant formats using 16b ints, and in a few places where the struct size is a multiple of 4 also using 32b ints. Currently only q4_k's aliases are used, but others will be used in subsequent commits. * vulkan: use larger loads in q5_k and q6_k shaders. Similar to the optimization I did in q4_k recently, this vectorizes some loads and reduces the number of bit twiddling instructions. * vulkan: use larger K step per iteration in mul_mat_vec. Add vec4 dequantization functions, and use them to do K=8 per iteration in mul_mat_vec. This uses 16b loads for the quant values and 128b loads for B which helps reduce the load on the memory system. The K_PER_ITER==2 logic is still there, just for F16/F32, and really only because they support unaligned sizes. Tweak the num_iters/unrolling logic to be simpler and catch a couple missed unrolling opportunities.	2024-11-20 08:11:00 +01:00
Neo Zhang Jianyu	ad21c9e1f1	update rel to 4040 (#10395) ... Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>	2024-11-20 13:54:25 +08:00
Anthony Van de Gejuchte	3952a221af	Fix missing file renames in Makefile due to changes in commit ae8de6d50a (#10413)	2024-11-19 23:18:17 +01:00
haopeng	42ae10bbcd	add cmake rvv support (#10411)	2024-11-19 21:10:31 +01:00
Georgi Gerganov	9fe0fb0626	sync : ggml	2024-11-19 20:03:21 +02:00
Plamen Minev	611fabd792	metal : fox offset integer overflows in im2col (ggml/1015) ... -- While running StableDiffusion.cpp locally with Metal some offsets overflow and results in incorrect calculations	2024-11-19 20:03:21 +02:00
PAB	12b0ad953a	metal : add GGML_UNARY_OP_ELU kernel (ggml/1018)	2024-11-19 20:03:21 +02:00
蕭澧邦	342397dc7e	cmake: force MSVC compiler charset to utf-8 (#9989)	2024-11-19 18:42:00 +01:00
bandoti	2a11b6b094	Add required ggml-base and backend libs to cmake pkg (#10407)	2024-11-19 17:10:30 +01:00
Diego Devesa	3ee6382d48	cuda : fix CUDA_FLAGS not being applied (#10403)	2024-11-19 14:29:38 +01:00
Georgi Gerganov	8e752a777b	llama : add check for KV cache shifts (#10401) ... ggml-ci	2024-11-19 13:29:26 +02:00
Shane A	a88ad007de	llama : add OLMo November 2024 support (#10394) ... * Add OLMo November 2024 constants * Add OLMo November 2024 converter * Add loading of OLMo November 2024 tensors and hyper parameters * Add building of OLMo November 2024 model	2024-11-19 11:04:08 +02:00
Romain Biessy	2a1507c162	sycl : Add option to set the SYCL architecture for all targets (#10266) ... * Add option to set the SYCL architecture for all targets * Convert GGML_SYCL_HIP_TARGET to the more generic GGML_SYCL_ARCH option * Document that setting GGML_SYCL_ARCH can improve the performance	2024-11-19 08:02:23 +00:00
Jeff Bolz	b3e585988f	vulkan: Optimize soft_max (#10301) ... * vulkan: Optimize soft_max Large soft_max could already saturate memory, but small/medium sizes were pretty slow. The bulk of the gains for them comes from using a smaller workgroup size, and making the workgroup size match the subgroup size also makes the barriers much cheaper. Cache some values in locals to avoid refetching/recomputing. And stamp out a few "template instantiations" so smaller cases will fully unroll. Add a missing early return for OOB rows. This happens when there are more than 512 rows and the dispatch is 512 x H. * vulkan: Further soft_max optimizations Restore the workgroup size of 512 case, use it for >1024. Use unrollable loops for more iteration counts.	2024-11-19 08:25:17 +01:00
Alberto Cabrera Pérez	557924f222	sycl: Revert MUL_MAT_OP support changes (#10385)	2024-11-19 08:50:04 +08:00
Diego Devesa	d3481e6316	cuda : only use native when supported by cmake (#10389)	2024-11-18 18:43:40 +01:00