357 Commits

Author	SHA1	Message	Date
Diego Devesa	dea5e86051	ggml : check tensor name lengths in gguf files (#10100)	2024-10-31 11:40:59 +01:00
Sergio López	1329c0a75e	kompute: add mul_mat_q4_k shader (#10097) ... This is a more or less direct translation from the Metal implementation to GLSL. Signed-off-by: Sergio Lopez <slp@redhat.com>	2024-10-31 11:09:52 +02:00
Sergio López	61408e7fad	kompute: add backend registry / device interfaces (#10045) ... Get in line with the other backends by supporting the newer backend/device registry interfaces. Signed-off-by: Sergio Lopez <slp@redhat.com>	2024-10-30 17:01:52 +01:00
Diego Devesa	b9e02e8184	ggml : fix memory leaks when loading invalid gguf files (#10094) ... * ggml : fix gguf string leak when reading kv pairs fails * ggml : avoid crashing with GGML_ABORT when the KV has an invalid type * ggml : avoid crashing on failed memory allocations when loading a gguf file	2024-10-30 14:51:21 +01:00
xctan	fc83a9e584	ggml : add Q4_0_8_8 RISC-V GEMV and GEMM kernels (#10029) ... * ggml : RISC-V vector gemv for q4_0_8x8 * ggml : Added WIP rvv q4_0_8x8 gemm * ggml : Added initial implementation of rvv gemm * ggml : optimize gemm to avoid register spillover * ggml : Fix GCC rvv load alignment issue * ggml : Format gemm rvv code * ggml : Fix a typo in RVV q4_0_8_8 GEMM	2024-10-30 09:00:40 +02:00
Diego Devesa	c5b0f4b5d9	llama : refactor model loader with backend registry (#10026)	2024-10-30 02:01:23 +01:00
Changyeon Kim	8f275a7c45	ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763) ... * ggml: Add POOL2D OP for GPU ACC to the Vulkan. - The MobileVLM model now supports inference acceleration through GPU by utilizing the Vulkan backend. - A GGML_OP_POOL_2D shader has been added. (Pooling) - The encoding performance of the CLIP model improved from 2.8s on the CPU to 0.7s on the GPU. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * [fix] Correct the incorrect order of the parameters. fix casting to int. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> --------- Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>	2024-10-29 09:52:56 +01:00
R0CKSTAR	524afeec9d	musa: workaround for Guilty Lockup in cleaning src0 (#10042) ... Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>	2024-10-28 10:02:48 +01:00
bssrdf	8c60a8a462	increase cuda_cpy block size (ggml/996) ... Co-authored-by: bssrdf <bssrdf@gmail.com>	2024-10-26 10:33:56 +03:00
Georgi Gerganov	668750357e	metal : support permuted matrix multiplicaions (#10033) ... * metal : support permuted matrix multiplicaions ggml-ci * cont : use nb01 directly for row steps ggml-ci * cont : add comments [no ci] * metal : minor refactor * metal : minor	2024-10-25 22:26:15 +03:00
Srihari-mcw	2f8bd2b901	llamafile : extend sgemm.cpp support for Q5_0 models (#10010)	2024-10-25 10:27:41 +03:00
Johannes Gäßler	167a515651	CUDA: fix insufficient buffer clearing for MMQ (#10032)	2024-10-24 14:40:23 +02:00
Johannes Gäßler	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 Gäßler	80273a306d	CUDA: fix 1D im2col, add tests (ggml/993)	2024-10-23 16:50:02 +03:00
Daniel Bevenius	c19af0acb1	ggml : remove redundant set of contexts used field (ggml/978) ... This commit removes the setting of the `used` field of the contexts in the global state (g_state) in `ggml_init`. The motivation for this change is that I believe that this additional initialization might not be required after the changes in Commit 45fc4fed0b9fb5b1af4a8525cbebb95e11208732 ("sync : latest changes from whisper.cpp"), which changed the initialization of the contexts field from `{ 0 }` to `{ { 0 } }`: ```console g_state = (struct ggml_state) { - /*.contexts =*/ { 0 }, + /*.contexts =*/ { { 0 } }, }; ``` My understanding is that the `{0}` initialization might not have zero-initialized all the nested fields in every array element because of compiler differences, and might have been the reason for having the explicit setting of the `used` fields to false.	2024-10-23 16:50:02 +03:00
Jun Hee Yoo	4c9388fb96	metal : add POOL2D and fix IM2COL (#9943) ... * add pool_2d Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * fix im2col and add unittest for N>=1024 Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * add tests for N % 1024 != 0 Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * remove trailing whitespaces Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * apply suggestions Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * apply more optimization - original IM2COL kernel + _ext with MIN() Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * apply review: change kernel name of pool_2d Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * apply review Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> * fix more formatting and enhance readability Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com> --------- Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com>	2024-10-23 13:33:45 +03:00
leo-pony	6b8447352d	[CANN] Adapt to dynamically loadable backends mechanism (#9970) ... * [CANN] Adapt to dynamically loadable backends mechanism * Fix the Bug: inference running result is garbled in debug running model for LM models who's type is Q4_0 class * Handle the review comments of this pull request	2024-10-22 16:16:01 +08:00
Georgi Gerganov	f594bc80ba	ggml : add asserts for type conversion in fattn kernels (#9971) ... ggml-ci	2024-10-21 16:20:46 +03:00
Radoslav Gerganov	d5ebd79c76	rpc : pack only RPC structs (#9959)	2024-10-21 13:35:40 +03:00
Neo Zhang Jianyu	1db8c84fc6	fix mul_mat_vec_q and *_vec_q error (#9939) ... Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>	2024-10-21 14:26:09 +08:00
Radoslav Gerganov	afd9909a64	rpc : backend refactoring (#9912) ... * rpc : refactor backend Use structs for RPC request/response messages * rpc : refactor server	2024-10-18 14:33:58 +03:00
Ouadie EL FAROUKI	87421a23e8	[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705) ... * implemented missing SYCL event APIs * sycl : Added device and backend reg interfaces * Restructured ggml-sycl.cpp	2024-10-18 06:46:16 +01:00
Ma Mingfei	60ce97c9d8	add amx kernel for gemm (#8998) ... add intel amx isa detection add vnni kernel for gemv cases add vnni and amx kernel support for block_q8_0 code cleanup fix packing B issue enable openmp fine tune amx kernel switch to aten parallel pattern add error message for nested parallelism code cleanup add f16 support in ggml-amx add amx kernels for QK_K quant formats: Q4_K, Q5_K, Q6_K and IQ4_XS update CMakeList update README fix some compilation warning fix compiler warning when amx is not enabled minor change ggml-ci move ggml_amx_init from ggml.c to ggml-amx/mmq.cpp ggml-ci update CMakeLists with -mamx-tile, -mamx-int8 and -mamx-bf16 ggml-ci add amx as an ggml-backend update header file, the old path for immintrin.h has changed to ggml-cpu-impl.h minor change update CMakeLists.txt minor change apply weight prepacking in set_tensor method in ggml-backend fix compile error ggml-ci minor change ggml-ci update CMakeLists.txt ggml-ci add march dependency minor change ggml-ci change ggml_backend_buffer_is_host to return false for amx backend ggml-ci fix supports_op use device reg for AMX backend ggml-ci minor change ggml-ci minor change fix rebase set .buffer_from_host_ptr to be false for AMX backend	2024-10-18 13:34:36 +08:00
Diego Devesa	f010b77a37	vulkan : add backend registry / device interfaces (#9721) ... * vulkan : add backend registry / device interfaces * llama : print devices used on model load	2024-10-17 02:46:58 +02:00
Gilad S.	2194200278	fix: allocating CPU buffer with size 0 (#9917)	2024-10-17 01:34:22 +02:00
Gilad S.	73afe681aa	fix: use vm_allocate to allocate CPU backend buffer on macOS (#9875) ... * fix: use `vm_allocate` to allocate CPU backend buffer on macOS * fix: switch to `posix_memalign` to keep existing `free()` usages work * feat: move `GGML_ALIGNED_MALLOC` to `ggml-backend-impl.h`, add support for `vm_allocate` on macOS * style: formatting * fix: move const outside of `#ifndef` * style: formatting * fix: unused var * fix: transform `GGML_ALIGNED_MALLOC` and `GGML_ALIGNED_FREE` into functions and add them to `ggml-impl.h` * fix: unused var * fix: page align to `GGUF_DEFAULT_ALIGNMENT` * fix: page align to `TENSOR_ALIGNMENT` * fix: convert `TENSOR_ALIGNMENT` to a macro * fix: increase page size to `32` on iOS * fix: iOS page size * fix: `hbw_posix_memalign` alignment	2024-10-17 00:36:51 +02:00
Daniel Bevenius	cd60b88bf7	ggml-alloc : remove buffer_id from leaf_alloc (ggml/987) ... This commit removes the buffer_id field from the leaf_alloc struct. The motivation for is that this field is only written to and never read/used as far as I can tell. Each tensor_alloc has a buffer_id field and this is what caused me to look into this more closely, to understand what the buffer_id in leaf_alloc was used for.	2024-10-16 11:28:01 +03:00
leo-pony	becfd387f6	[CANN] Fix cann compilation error (#9891) ... Fix cann compilation error after merging llama.cpp supports dynamically loadable backends.	2024-10-16 08:51:46 +08:00
agray3	13dca2a54a	Vectorize load instructions in dmmv f16 CUDA kernel (#9816) ... * Vectorize load instructions in dmmv f16 CUDA kernel Replaces scalar with vector load instructions, which substantially improves performance on NVIDIA HBM GPUs, e.g. gives a 1.27X overall speedup for Meta-Llama-3-8B-Instruct-F16 BS1 inference evaluation on H100 SXM 80GB HBM3. On GDDR GPUs, there is a slight (1.01X) speedup. * addressed comment * Update ggml/src/ggml-cuda/dmmv.cu Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>	2024-10-14 02:49:08 +02:00
Diego Devesa	96776405a1	ggml : move more prints to the ggml log system (#9839) ... * ggml : move more prints to the ggml log system * show BLAS OpenMP warnings in all builds using debug print	2024-10-11 15:34:45 +02:00
Diego Devesa	0e9f760eb1	rpc : add backend registry / device interfaces (#9812) ... * rpc : add backend registry / device interfaces * llama : add llama_supports_rpc API * ggml_backend_rpc_start_rpc_server -> ggml_backend_rpc_start_server	2024-10-10 20:14:55 +02:00
R0CKSTAR	cf8e0a3bb9	musa: add docker image support (#9685) ... * mtgpu: add docker image support Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * mtgpu: enable docker workflow Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> --------- Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>	2024-10-10 20:10:37 +02:00
Diego Devesa	dca1d4b58a	ggml : fix BLAS with unsupported types (#9775) ... * ggml : do not use BLAS with types without to_float * ggml : return pointer from ggml_internal_get_type_traits to avoid unnecessary copies * ggml : rename ggml_internal_get_type_traits -> ggml_get_type_traits it's not really internal if everybody uses it	2024-10-08 14:21:43 +02:00
Diego Devesa	6374743747	ggml : add backend registry / device interfaces to BLAS backend (#9752) ... * ggml : add backend registry / device interfaces to BLAS backend * fix mmap usage when using host buffers	2024-10-07 21:55:08 +02:00
Andrew Minh Nguyen	f1af42fa8c	Update building for Android (#9672) ... * docs : clarify building Android on Termux * docs : update building Android on Termux * docs : add cross-compiling for Android * cmake : link dl explicitly for Android	2024-10-07 09:37:31 -07:00
Georgi Gerganov	d5ac8cf2f2	ggml : add metal backend registry / device (#9713) ... * ggml : add metal backend registry / device ggml-ci * metal : fix names [no ci] * metal : global registry and device instances ggml-ci * cont : alternative initialization of global objects ggml-ci * llama : adapt to backend changes ggml-ci * fixes * metal : fix indent * metal : fix build when MTLGPUFamilyApple3 is not available ggml-ci * fix merge * metal : avoid unnecessary singleton accesses ggml-ci * metal : minor fix [no ci] * metal : g_state -> g_ggml_ctx_dev_main [no ci] * metal : avoid reference of device context in the backend context ggml-ci * metal : minor [no ci] * metal : fix maxTransferRate check * metal : remove transfer rate stuff --------- Co-authored-by: slaren <slarengh@gmail.com>	2024-10-07 18:27:51 +03:00
Paul Tsochantaris	96b6912103	metal : single allocation of encode_async block (#9747) ... * Single allocation of encode_async block with non-ARC capture in ggml-metal.m * Moving Block_release to the deallocation code * Release encode block when re-setting encoding buffer count if needed * Update ggml/src/ggml-metal.m --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-10-07 15:26:31 +03:00
SRHMorris	b0915d5b51	vulkan : retry allocation with fallback flags (whisper/2451) ... Co-authored-by: Samuel Morris <samuel.morris@artlist.io>	2024-10-06 12:52:11 +03:00
Georgi Gerganov	905f5485b2	metal : zero-init buffer contexts (whisper/0)	2024-10-05 15:53:00 +03:00
Daniel Bevenius	55951c018d	ggml : fix typo in example usage ggml_gallocr_new (ggml/984)	2024-10-04 18:50:05 +03:00
Diego Devesa	ff565769f2	ggml : fixes after sync (ggml/983) ... ggml : remove test-backend-buffer ggml : fix CUDA build warnings	2024-10-04 18:50:04 +03:00
Georgi Gerganov	d5ed2b929d	metal : remove abort (skip) (ggml/0)	2024-10-03 21:18:19 +03:00
Johannes Gäßler	fabdc3bda3	ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)	2024-10-03 21:17:26 +03:00
Johannes Gäßler	eee39bdc96	ggml: refactor cross entropy loss CPU impl. (ggml/976)	2024-10-03 21:17:26 +03:00
Jack Mousseau	5d5ab1e5cc	metal : fix compute pass descriptor autorelease crash (#9718)	2024-10-03 21:01:46 +03:00
Diego Devesa	a7ad553513	ggml-backend : add device description to CPU backend (#9720)	2024-10-03 17:39:18 +02:00
bandoti	d6fe7abf04	ggml: unify backend logging mechanism (#9709) ... * Add scaffolding for ggml logging macros * Metal backend now uses GGML logging * Cuda backend now uses GGML logging * Cann backend now uses GGML logging * Add enum tag to parameters * Use C memory allocation funcs * Fix compile error * Use GGML_LOG instead of GGML_PRINT * Rename llama_state to llama_logger_state * Prevent null format string * Fix whitespace * Remove log callbacks from ggml backends * Remove cuda log statement	2024-10-03 17:39:03 +02:00
Ouadie EL FAROUKI	5639971466	Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)	2024-10-03 07:50:44 +01:00
Diego Devesa	c83ad6d01e	ggml-backend : add device and backend reg interfaces (#9707) ... Co-authored-by: Johannes Gäßler <johannesg@5d6.de>	2024-10-03 01:49:47 +02:00
Alberto Cabrera Pérez	f536f4c439	[SYCL] Initial cmake support of SYCL for AMD GPUs (#9658) ... sycl: initial cmake support of SYCL for AMD GPUs	2024-10-02 13:57:18 +01:00
Radoslav Gerganov	00b7317e63	vulkan : do not use tensor->extra (#9407) ... * vulkan : do not use tensor->extra This patch allows using the Vulkan backend with the RPC backend as tensor->extra is no longer used. Ref: #8536 * Adapt GGML_VULKAN_CHECK_RESULTS to extra removal (#2) --------- Co-authored-by: 0cc4m <picard12@live.de>	2024-10-02 13:49:16 +03:00
Johannes Gäßler	e98c1c188e	test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)	2024-10-01 16:07:40 +03:00
Salvatore Mesoraca	cb00020504	vulkan : mul_mat: fix UB with small warps (ggml/952) ... When the device's warp size is less than 16, it is possible for loadstride_a (mul_mm.comp:114) and loadstride_b (mul_mm.comp:115) to be set to 0. Because they are calculated as: the workgroup size, multiplied by LOAD_VEC_* (which can be 1) and divided by 16. And the workgroup size is set to be the same as the warp/subgroup size. The loadstride_* variables are used as increments in the loops that populate the buffers used for the multiplication. When they are 0 they cause an infinite loop. But infinite loops without side-effects are UB and the values of loadstride_* are known at compile time. So, the compiler quietly optimizes all the loops away. As a consequence, the buffers are not populated and the multiplication result is just a matrix with all elements set to 0. We prevent the UB by making sure that the workgroup size will never be less than 16, even if our device has a smaller warp size (e.g. 8). Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>	2024-10-01 16:07:39 +03:00
Borislav Stanimirov	6c5322481a	ggml : fix ggml_cast (ggml/973)	2024-10-01 16:07:39 +03:00
Johannes Gäßler	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
Georgi Gerganov	cad341d889	metal : reduce command encoding overhead (#9698) ... * metal : reduce command encoding overhead ggml-ci * metal : add comments	2024-10-01 16:00:25 +03:00
Georgi Gerganov	c919d5db39	ggml : define missing HWCAP flags (#9684) ... ggml-ci Co-authored-by: Willy Tarreau <w@1wt.eu>	2024-09-29 21:18:23 +03:00
Johannes Gäßler	aaa4099925	CUDA: remove bad assert (ggml/972)	2024-09-29 21:15:37 +03:00
Jeff Bolz	641002fba8	vulkan : multithread pipeline creation (ggml/963)	2024-09-29 21:15:37 +03:00
Jeff Bolz	0de8b203f1	vulkan : fix build for GGML_VULKAN_RUN_TESTS, add TFLOPS to log (ggml/961)	2024-09-29 21:15:37 +03:00
Salvatore Mesoraca	544f409b4b	vulkan : argsort barriers must be under uniform control flow (ggml/951) ... a return before a barrier (that happens only in some threads in a workgroup) leads to UB. While the old code actually works on some devices, it fails on some others (i.e. "smaller" GPUs). BTW, I think it would be better to set specialization constants when the graph is built, in that way the local workgroup could be sized appropriately. But it would take a lot of work. Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>	2024-09-29 21:15:37 +03:00
Georgi Gerganov	6084bfb261	ggml : fix GGML_MAX_N_THREADS + improve formatting (ggml/969)	2024-09-29 21:15:35 +03:00
Dan Johansson	6a0f779484	ggml : add run-time detection of neon, i8mm and sve (#9331) ... * ggml: Added run-time detection of neon, i8mm and sve Adds run-time detection of the Arm instructions set features neon, i8mm and sve for Linux and Apple build targets. * ggml: Extend feature detection to include non aarch64 Arm arch * ggml: Move definition of ggml_arm_arch_features to the global data section	2024-09-28 15:06:16 +03:00
Markus Tavenrath	89f9944981	Enable use to the rebar feature to upload buffers to the device. (#9251)	2024-09-28 12:05:05 +02:00
R0CKSTAR	7691654c68	mtgpu: enable VMM (#9597) ... Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>	2024-09-26 03:27:40 +02:00
Charles Xu	1e43630218	ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (#9217) ... * ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels * added fallback mechanism when the offline re-quantized model is not optimized for the underlying target. * fix for build errors * remove prints from the low-level code * Rebase to the latest upstream	2024-09-25 16:12:20 +03:00
Dou Xinpeng	904837e0cb	cann: fix crash when llama-bench is running on multiple cann devices (#9627)	2024-09-25 11:30:38 +08:00
Eric Zhang	70392f1f81	ggml : add AVX512DQ requirement for AVX512 builds (#9622)	2024-09-24 11:03:21 +03:00
Georgi Gerganov	c038931615	examples : adapt to ggml.h changes (ggml/0) ... ggml-ci	2024-09-24 11:00:52 +03:00
Georgi Gerganov	cea1486ecf	log : add CONT level for continuing previous log entry (#9610)	2024-09-24 10:15:35 +03:00
Max Krasnyansky	c087b6f11d	threads: fix msvc build without openmp (#9615) ... We're missing atomic_thread_fence() in MSVC builds when openmp is disabled.	2024-09-23 21:18:48 -07:00
Ivan	116efee0ee	cuda: add q8_0->f32 cpy operation (#9571) ... llama: enable K-shift for quantized KV cache It will fail on unsupported backends or quant types.	2024-09-24 02:14:24 +02:00
Max Krasnyansky	f0c7b5edf8	threads: improve ggml_barrier scaling with large number of threads (#9598) ... Make sure n_barrier and n_barrier_passed do not share the cache line to avoid cache line bouncing. This optimization shows performance improvements even for n_threads <= 8 cases. Resurect TSAN (Thread Sanitizer) check so that we can avoid doing expensive read-modify-write in the normal case and just use thread-fence as originally intended. --- Here is the original description and suggestions from Willy Tarreau : There's currently some false sharing between n_barrier and n_barrier_passed that is amplified in ggml_barrier() by the fact that all threads need to increment n_barrier when entering, while all previous threads continue to read n_barrier_passed, waiting for the last one to release them all. The side effect is that all these readers are slowing down all new threads by making the cache line bounce back and forth between readers and writers. Just placing them in two distinct cache lines is sufficient to boost the performance by 21% on a 80-core ARM server compared to the no-openmp version, and by 3% compared to the openmp version. Note that the variables could have been spread apart in the structure as well, but it doesn't seem that the size of this threadpool struct is critical so here we're simply aligning them. Finally, the same issue was present when leaving the barrier since all threads had to update the n_barrier_passed counter, though only one would add a non-zero value. This alone is responsible for half of the cost due to undesired serialization. It might be possible that using a small array of n_barrier counters could make things even faster on many-core systems, but it would likely complicate the logic needed to detect the last thread. Co-authored-by: Willy Tarreau <w@1wt.eu>	2024-09-23 11:42:43 -07:00
Srihari-mcw	1e7b9299c6	ggml : AVX512 gemm for Q4_0_8_8 (#9532) ... * AVX512 version of ggml_gemm_q4_0_8x8_q8_0 * Remove zero vector parameter passing * Rename functions and rearrange order of macros * Edit commments * style : minor adjustments * Update x to start from 0 --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-23 17:06:38 +03:00
Georgi Gerganov	bf9c1013ac	metal : use F32 prec for K*Q in vec FA (#9595) ... ggml-ci	2024-09-23 11:27:47 +03:00
Akarshan Biswas	e62e9789cd	Revert "[SYCL] fallback mmvq (#9088)" (#9579) ... This reverts commit 50addec9a5.	2024-09-23 11:28:06 +08:00
R0CKSTAR	c35e586ea5	musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526) ... * mtgpu: add mp_21 support Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * mtgpu: disable flash attention on qy1 (MTT S80); disable q3_k and mul_mat_batched_cublas Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * mtgpu: enable unified memory Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * mtgpu: map cublasOperation_t to mublasOperation_t (sync code to latest) Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> --------- Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>	2024-09-22 16:55:49 +02:00
Molly Sophia	912c331d3d	Fix merge error in #9454 (#9589) ... Signed-off-by: Molly Sophia <mollysophia379@gmail.com>	2024-09-22 15:26:50 +02:00
Johannes Gäßler	a5b57b08ce	CUDA: enable Gemma FA for HIP/Pascal (#9581)	2024-09-22 09:34:52 +02:00
Molly Sophia	2a63caaa69	RWKV v6: RWKV_WKV op CUDA implementation (#9454) ... * ggml: CUDA unary op EXP Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * ggml: rwkv_wkv op CUDA impl Signed-off-by: Molly Sophia <mollysophia379@gmail.com> --------- Signed-off-by: Molly Sophia <mollysophia379@gmail.com>	2024-09-22 04:29:12 +02:00
slaren	d09770cae7	ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)	2024-09-21 14:24:23 +02:00
agray3	41f477879f	Update CUDA graph on scale change plus clear nodes/params (#9550) ... * Avoid using saved CUDA graph if scale changes and reset nodes/params on update Fixes https://github.com/ggerganov/llama.cpp/issues/9451 * clear before resize	2024-09-21 02:41:07 +02:00
Georgi Gerganov	d13edb17ed	ggml : fix builds (#0) ... ggml-ci	2024-09-20 21:15:05 +03:00
Georgi Gerganov	27609c49b9	ggml : fix trailing whitespace (#0) ... ggml-ci	2024-09-20 21:15:05 +03:00
Johannes Gäßler	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
Georgi Gerganov	a6809c6a2e	examples : add null threadpool args where needed (ggml/0) ... ggml-ci	2024-09-20 21:15:05 +03:00
Johannes Gäßler	5cb12f6839	CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562)	2024-09-20 18:35:35 +02:00
slaren	64c6af3195	ggml : fix n_threads_cur initialization with one thread (#9538) ... * ggml : fix n_threads_cur initialization with one thread * Update ggml/src/ggml.c --------- Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>	2024-09-18 10:13:08 -07:00
Max Krasnyansky	0226613853	threadpool : skip polling for unused threads (#9461) ... * threadpool: skip polling for unused threads Currently all threads do N polling rounds even if only 1 thread is active (n_threads_cur == 1). This commit adds a check to skip the polling for unused threads (ith >= n_threads_cur). n_threads_cur is now an atomic_int to explicitly tell thread sanitizer that it is written from one thread and read from other threads (not a race conditions). * threadpool: further simplify and improve ggml_barrier Avoid using strict memory order while polling, yet make sure that all threads go through full memory barrier (memory fence) on ggml_barrier entrace and exit. * threads: add simple barrier test This test does lots of small, parallel matmul ops where the barriers in between dominate the overhead. * threadpool: improve thread sync for new-graphs Using the same tricks as ggml_barrier. All the polling is done with relaxed memory order to keep it efficient, once the new graph is detected we do full fence using read-modify-write with strict memory order. * threadpool: improve abort handling Do not use threadpool->ec (exit code) to decide whether to exit the compute loop. threadpool->ec is not atomic which makes thread-sanitizer rightfully unhappy about it. Instead introduce atomic threadpool->abort flag used for this. This is consistent with how we handle threadpool->stop or pause. While at it add an explicit atomic_load for n_threads_cur for consistency. * test-barrier: release threadpool before releasing the context fixes use-after-free detected by gcc thread-sanitizer on x86-64 for some reason llvm sanitizer is not detecting this issue.	2024-09-17 11:19:46 +03:00
slaren	23e0d70bac	ggml : move common CPU backend impl to new header (#9509)	2024-09-16 16:22:07 +02:00
Michael Podvitskiy	a6a3a5c531	ggml : link MATH_LIBRARY not by its full path (#9339)	2024-09-16 14:06:50 +03:00
Georgi Gerganov	19514d632e	cmake : do not hide GGML options + rename option (#9465) ... * cmake : do not hide GGML options ggml-ci * build : rename flag GGML_CUDA_USE_GRAPHS -> GGML_CUDA_GRAPHS for consistency ggml-ci	2024-09-16 10:27:50 +03:00
Eve	5c3d0f1824	ggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422) ... * squashed readd my iq4_nl sgemm PR https://github.com/ggerganov/llama.cpp/pull/8049 have ggml_vec_dot_q4_0 do two blocks per loop for avx try out f16c ggml_vec_dot_iq4_nl, but it's not really faster. as per https://github.com/ggerganov/llama.cpp/pull/8549 we can calculate several blocks at a time with no issue * shuffle * remove f16c iq4_nl as i cant make it faster than before	2024-09-16 09:48:24 +03:00
Georgi Gerganov	c4965a64f7	metal : handle zero-sized allocs (#9466)	2024-09-16 09:05:56 +03:00
Georgi Gerganov	6262d13e0b	common : reimplement logging (#9418) ... https://github.com/ggerganov/llama.cpp/pull/9418	2024-09-15 20:46:12 +03:00
Michael Podvitskiy	6988da94a2	cmake : correct order of sycl flags (#9497)	2024-09-15 19:55:52 +03:00
Michael Podvitskiy	7596487beb	cmake : try to fix sycl+intel build (#9487)	2024-09-15 10:06:38 +03:00
Yuri Khrustalev	822b6322de	ggml : ggml_type_name return "NONE" for invalid values (#9458) ... When running on Windows, the quantization utility attempts to print the types that are not set which leads to a crash.	2024-09-14 12:54:37 +03:00
Georgi Gerganov	1f4111e540	cmake : use list(APPEND ...) instead of set() + dedup linker (#9463) ... * cmake : use list(APPEND ...) instead of set() + dedup linker ggml-ci * cmake : try fix sycl * cmake : try to fix sycl 2 * cmake : fix sycl build (#9469) * try fix sycl build * use CMAKE_CXX_FLAGS as a string variable --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * one more CMAKE_CXX_FLAGS fix (#9471) --------- Co-authored-by: Michael Podvitskiy <podvitskiymichael@gmail.com>	2024-09-14 10:55:05 +03:00
Dou Xinpeng	e6b7801bd1	cann: Add host buffer type for Ascend NPU (#9406) ... * feat: Add host buffer type for Ascend NPU(CANN backend) * fix some checking errors * Add a few comments	2024-09-12 19:46:43 +08:00
Ahmad Tameem	2b00fa7997	riscv : modify Makefile and add a RISCV_VECT to print log info (#9442) ... - Added ggml_cpu_has_riscv_v() in GGML to print system info in log - Modified Makefile to only use flag when cross compiling for RISC-V	2024-09-12 14:24:31 +03:00
Georgi Gerganov	d6a04f872d	ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408) ... * ggml : hide ggml_object, ggml_cgraph, ggml_hash_set ggml-ci * ggml : add ggml-impl.h to backends * ggml : fix compiler warnings ggml-ci * ggml : add assert upon adding nodes	2024-09-12 14:23:49 +03:00
Xinpeng Dou	df4b7945ae	cann: Fix error when running a non-exist op (#9424)	2024-09-12 09:02:35 +08:00
Johannes Gäßler	5af118efda	CUDA: fix --split-mode row race condition (#9413)	2024-09-11 10:22:40 +02:00
R0CKSTAR	b34e023480	musa: remove Clang builtins mapping (#9421) ... Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>	2024-09-11 03:46:55 +02:00
Alberto Cabrera Pérez	51b6038636	sycl : update support conditions (#9394) ... * sycl : update support condition to im2col Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com> * Added TODO to remind supporting FP32 im2col --------- Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com>	2024-09-11 08:53:42 +08:00
Georgi Gerganov	00ba2ff781	metal : fix compile warning with GGML_METAL_NDEBUG (#0)	2024-09-10 10:17:43 +03:00
Radoslav Gerganov	293bebe077	rpc : fix segfault with nkvo (#9389) ... * rpc : fix nkvo * rpc : buf_size must not be static ref: #9337 --------- Co-authored-by: slaren <slarengh@gmail.com>	2024-09-09 18:40:10 +03:00
Prashant Vithule	5fac4d5764	ggml : vector length agnostic SVE support (#9290) ... * Implemented vector length agnostic SVE using switch case for 512-bit, 256-bit, 128-bit vector lengths * Implemented vector length agnostic SVE using switch case for 512-bit, 256-bit, 128-bit vector lengths * Removed WhiteSpaces * ggml : style changes + fix 512-bit nb loop check - fix local scope in switch cases - consistent predicate names - empty lines when necessary - opening braces, spaces - const-correctness - add asserts * Update ggml/src/ggml-quants.c Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-09 18:37:18 +03:00
Johannes Gäßler	8e6e2fbe14	CUDA: fix variable name conflict for Windows build (#9382)	2024-09-09 14:22:53 +02:00
Markus Tavenrath	daa9623ab0	Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend by submitting smaller cmdbuffers early. (#9118) ... * Overlap cmdbuffer creation and cmdbuffer execution in Vulkan backend by submitting smaller cmdbuffers early. * fix compile issues * Fix issues where the last submit wasn't executed or handled properly. * remove trailing whitespace * Repair GGML_VULKAN_CHECK_RESULTS * Increase submit counter only if actual work has been submitted and increase submit count to 100. * Fix some nodes are not checked with GGML_VULKAN_CHECK_RESULTS enabled.	2024-09-08 21:43:48 +02:00
Georgi Gerganov	e079bffb66	cuda : fix FA Q src index (1 -> 0) (#9374)	2024-09-08 22:01:02 +03:00
Neo Zhang Jianyu	2a358fb0c4	[SYCL] add check malloc result on device (#9346) ... * add check malloc result on device * update for review comments, check all malloc_device() result --------- Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>	2024-09-08 19:05:29 +08:00
Georgi Gerganov	a876861455	metal : update support condition for im2col + fix warning (#0)	2024-09-08 11:05:55 +03:00
Salvatore Mesoraca	406c1a32a1	vulkan: add dryrun support to sin and cos ops (ggml/947) ... sin and cos failed test-backend-ops because they tried to dereference a context pointer that is null on dry runs. This commit prevents that segfault. Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>	2024-09-08 11:05:55 +03:00
Salvatore Mesoraca	9cb9260861	vulkan: correctly report support for OP_CONT (ggml/946) ... test-backend-ops fails because ggml_cont aborts when invoked passing an unsupported type. This commit makes ggml_cont tests pass Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>	2024-09-08 11:05:55 +03:00
Johannes Gäßler	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 Gäßler	dbbebcab33	ggml: fix ggml_graph_cpy undefined behavior (ggml/943)	2024-09-08 11:05:55 +03:00
Georgi Gerganov	ba1cf846ed	cann : fix doxy (ggml/0)	2024-09-08 11:05:55 +03:00
Mengqing Cao	d2d3200b38	cann : add Ascend NPU support (whisper/2336) ... * enable Ascend NPU in src/whisper.cpp * sync test-backend-ops with llama.cpp	2024-09-08 11:05:55 +03:00
Georgi Gerganov	51d964a4ef	cuda : mark BF16 CONT as unsupported	2024-09-08 11:05:55 +03:00
Salvatore Mesoraca	efe6a83e30	ggml : fix cont with transposed tensors when one dimension is 1 (ggml/934) ... * ggml_cont: fix issue with transposed tensors when one dimension is 1 when using multiple threads, it is not enough to check for the tensors to be contiguous for ggml_compute_forward_dup_same_cont to work correctly. The tensors strides also need to match. Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com> * Add ggml_cont tests Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com> * Remove dead code it isn't possible to reach this code because all these functions are invoked by ggml_compute_forward_dup if and only if src0->type != dst->type Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com> * Make ggml_compute_forward_dup_same_cont work with contiguous tensors Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com> --------- Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-08 11:05:55 +03:00
Eve	e536426ded	llamafile : disable sgemm for batch-size 1 (#9330)	2024-09-07 22:02:26 +03:00
slaren	e32d0816ed	ggml : always check bounds on get_rows operations (#9354)	2024-09-07 20:23:07 +02:00
Xuan Son Nguyen	947538acb8	ggml : fix missing cpu_set_t on emscripten (#9336) ... * ggml : fix missing cpu_set_t on emscripten * better version * bring back android part	2024-09-07 12:01:34 +02:00
Changyeon Kim	409dc4f8bb	ggml : fix build break for the vulkan-debug (#9265) ... - windows build : Ok. - linux build : Ok. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com>	2024-09-06 15:54:50 +03:00
Markus Tavenrath	8ebe8ddebd	Improve Vulkan shader build system (#9239) ... * Improve Vulkan shader builds system - Add dependency to vulkan-shaders-gen to rebuild shaders when changing the shader compilation utility. - Add option to generate debug info for Vulkan shaders to provide shader source to Vulkan shader profiling tools * remove not required self dependency	2024-09-06 08:56:17 +02:00
compilade	9bc6db28d0	ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151) ... * ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b * ggml-quants : faster 1.625 bpw AVX2 vec_dot Not using a lookup table anymore makes it match q4_0 speed. * gguf-py : fix formatting * llama : remove spaces on empty line * ggml-quants : subtract 1 when back in epi8 This makes the 1.625 bpw type go faster than q4_0. Still not the fastest. * ggml-quants : Q2_2 now faster than Q4_K on with AVX2 * ggml-quants : cleanup Q1_3 code formatting * ggml-quants : ARM NEON vec_dot for q2_2 and q1_3 * ggml-quants : use ceiling division when quantizing q1_3 * convert-hf : simplify BitNet pre-quantization This still results in the exact same tensor weights and scales, but it reveals some weirdness in the current algorithm. * convert-hf : allow converting the weird BitNet 1.3B Its FFN size is 5460 which is not convenient. The offending tensors are kept in F16, which makes the final model 5.01 bpw. * bitnet : replace 1.58b with b1.58, as in the paper * ggml-quants : fix build failure on Windows * ggml-quants : attempt to fix Arm 32-bit support * ggml : add some informative comments in q1_3 vec_dot * ggml : add TQ1_0 and TQ2_0 ternary quantization types * ggml : even faster TQ2_0 * ggml : also faster TQ1_0 Same optimization as for TQ2_0 by offsetting the sum instead of the weights. This makes TQ1_0 almost as fast as Q8_0 on AVX2. * ggml : fix build issues in certain environments * ggml : add NEON vec_dot implementation for TQ1_0 and TQ2_0 * ggml : avoid directly using vmlal_high_s8, for 32-bit ARM compat The compiler seems smart enough to use the same instruction even when using vget_high_s8 instead. * ggml : remove q1_3 and q2_2 No more 1.625 bpw and 2.000 bpw, now instead using 1.6875 bpw and 2.0625 bpw with TQ1_0 and TQ2_0, respectively. * llama : remove the separate scale tensors of BitNet b1.58 They won't be needed, since the remaining ternary quant types have built-in scales. * ggml-quants : rename fields of TQ1_0 and TQ2_0 structs for consistency * ggml-quants : allow using vdotq_s32 in TQ2_0 vec_dot Not yet tested on hardware which supports it, might not work or might not even compile. But also it might. It should make the performance better on recent ARM CPUs. * ggml-quants : remove comment about possible format change of TQ2_0 Making it slightly more convenient for AVX512 but less convenient for everything else is not worth the trouble. * gguf-py : Numpy (de)quantization for TQ1_0 and TQ2_0 * ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0 This does not change anything for ternary models, since their values should never end up being in halfway cases anyway. * convert : allow direct conversion to TQ1_0 and TQ2_0 The token embeddings and output tensors are kept in F16 to allow quantizing them to Q4_K and Q6_K with llama-quantize. * llama : handle fallback for TQ1_0 and TQ2_0 with Q4_0 Q4_0 is not completely symmetric (so not lossless for ternary models), but it should be good enough. * ggml-quants : allow using ARM dot product instructions for TQ1_0 * ggml-quants : deduplicate TQ1_0 and TQ2_0 __ARM_FEATURE_DOTPROD support * ggml : remove unused ggml_mul special case It would otherwise conflict with the more general optimization coming with Mamba-2. * ggml : handle TQ1_0 and TQ2_0 in dequantization-based operators * test-backend-ops : add TQ1_0 and TQ2_0 comments for later Not yet adding uncommented, because some backends like SYCL and Metal do not properly handle unknown types in supports_op for GGML_OP_MUL_MAT. (and Metal also doesn't handle it with GGML_OP_GET_ROWS) Support for TQ1_0 and TQ2_0 for other backends than CPU will be added in follow-up pull requests.	2024-09-05 21:48:47 -04:00
slaren	4db04784f9	cuda : fix defrag with quantized KV (#9319)	2024-09-05 11:13:11 +02:00
Srihari-mcw	581c305186	ggml : AVX2 support for Q4_0_8_8 (#8713) ... * Add AVX2 based implementations for quantize_q8_0_4x8, ggml_gemv_q4_0_8x8_q8_0 and ggml_gemm_q4_0_8x8_q8_0 functions * Update code to fix issues occuring due to non alignment of elements to be processed as multiple of 16 in MSVC * Update comments and indentation * Make updates to reduce number of load instructions	2024-09-04 19:51:22 +03:00
Ouadie EL FAROUKI	5910ea9427	[SYCL] Fix DMMV dequantization (#9279) ... Fixed dmmv dequant for ncols== GGML_SYCL_DMMV_X	2024-09-04 16:26:33 +01:00
yuri@FreeBSD	f771d064a9	ggml : add pthread includes on FreeBSD (#9258)	2024-09-02 18:25:30 +03:00
Molly Sophia	8f1d81a0b6	llama : support RWKV v6 models (#8980) ... * convert_hf_to_gguf: Add support for RWKV v6 Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Add RWKV tokenization * Fix build Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Do not use special tokens when matching in RWKV tokenizer * Fix model loading * Add (broken) placeholder graph builder for RWKV * Add workaround for kv cache * Add logits conversion to rwkv5 * Add rwkv5 layer norms * Add time mix KVRG & correct merge mistake * Add remaining time mix parameters * Add time mix output loading * Add placeholder llm_build_time_mix * Fix build Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Load more tensors for rwkv v6 Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Fix rwkv tokenizer Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * ggml: Add unary operator Exp Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * RWKV v6 graph building Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Add ``rescale_every_n_layers`` parameter Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Add ``wkv.head_size`` key for RWKV so it doesn't reuse Mamba ssm parameters Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Fix offloading layers to CUDA Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Fix parallel inferencing for RWKV Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Remove trailing whitespaces Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * build_rwkv: Avoid using inplace operations Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * convert_hf_to_gguf: rwkv: Avoid using ``eval`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * convert_hf_to_gguf: rwkv tokenizer: Don't escape sequences manually Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Update convert_hf_to_gguf.py Co-authored-by: compilade <git@compilade.net> * ggml: Add backward computation for unary op ``exp`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Update convert_hf_to_gguf.py Co-authored-by: compilade <git@compilade.net> * Update convert_hf_to_gguf.py Co-authored-by: compilade <git@compilade.net> * Use MODEL_ARCH.RWKV6 instead of MODEL_ARCH.RWKV Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * build_rwkv6: Simplify graph Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Detect model.type Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Fix tensor loading for 7B/14B models Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Fix group_norm assertion failure with Metal Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Clean up Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Add quantization tensor exclusion Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Use the new advanced batch splits Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Update src/llama.cpp Co-authored-by: compilade <git@compilade.net> * llama: rwkv6: Use ``ggml_norm`` instead of ``ggml_group_norm`` Co-authored-by: compilade <git@compilade.net> * llama: rwkv6: Apply code style and misc changes Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * converter: Use class name ``Rwkv6Model`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Make use of key ``feed_forward_length`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Add kv ``time_mix_extra_dim`` and ``time_decay_extra_dim`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * converter: Match ``new_name`` instead of ``name`` for float32 explicit tensors Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Keep ``time_mix_w1/w2`` as F32 Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Remove unused nodes Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Apply code format changes Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * llama: rwkv6: Add lora for some supported tensors Currently att.key/receptance/value/gate/output, ffn.receptance/key/value, as well as head.weight Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * rwkv : speed-up tokenization using trie * minor : style + indentation * llama: rwkv6: Avoid division by zero Co-authored-by: compilade <git@compilade.net> * ggml: rwkv_wkv: Avoid copying the state Signed-off-by: Molly Sophia <mollysophia379@gmail.com> --------- Signed-off-by: Molly Sophia <mollysophia379@gmail.com> Co-authored-by: Layl Bongers <3094382+LaylBongers@users.noreply.github.com> Co-authored-by: compilade <git@compilade.net> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-01 17:38:17 +03:00
Srihari-mcw	ea5d7478b1	sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908)	2024-08-31 11:20:35 +03:00
Faisal Zaghloul	42c76d1358	Threadpool: take 2 (#8672) ... * Introduce ggml_compute_threadpool - OpenMP functional: check - Vanilla ggml functional: Check - ggml w/threadpool functional: Check - OpenMP no regression: No glaring problems - Vanilla ggml no regression: No glaring problems - ggml w/threadpool no regression: No glaring problems * Minor fixes * fixed use after release bug * fixed a harmless race condition * Fix Android bulid issue * fix more race conditions * fix deadlock for cases where cgraph.n_nodes == 1 and fix --poll case * threadpool: use cpu_get_num_math to set the default number of threadpool threads This way we avoid using E-Cores and Hyperthreaded siblings. * bench: create fresh threadpool for each test For benchmarking it's better to start a fresh pool for each test with the exact number of threads needed for that test. Having larger pools is suboptimal (causes more load, etc). * atomics: always use stdatomics with clang and use relaxed memory order when polling in ggml_barrier This also removes sched_yield() calls from ggml_barrier() to match OpenMP behavior. * threadpool: make polling the default to match openmp behavior All command line args now allow for setting poll to 0 (false). * threadpool: do not wakeup threads in already paused threadpool * fix potential race condition in check_for_work * threadpool: do not create two threadpools if their params are identical * threadpool: reduce pause/resume/wakeup overhead in common cases We now start threadpool in paused state only if we have two. The resume is now implicit (ie new work) which allows for reduced locking and context-switch overhead. * threadpool: add support for hybrid polling poll params (--poll, ...) now specify "polling level", i.e. how aggresively we poll before waiting on cond.var. poll=0 means no polling, 1 means poll for 128K rounds then wait, 2 for 256K rounds, ... The default value of 50 (ie 50x128K rounds) seems like a decent default across modern platforms. We can tune this further as things evolve. * threadpool: reduce the number of barrier required New work is now indicated with an atomic counter that is incremented for each new graph that needs to be computed. This removes the need for extra barrier for clearing the "new_work" and removes the special case for trivial graphs. * threadpool: remove special-casing for disposable threadpools With the efficient hybrid polling there is no need to make disposable pools any different. This simplifies the overall logic and reduces branching. Include n_threads in debug print for disposable threadpool. Declare pause and stop flags as atomic_bool This doesn't actually generate any memory barriers and simply informs the thread sanitizer that these flags can be written & read by different threads without locking. * threadpool: do not clear barrier counters between graphs computes (fixes race with small graphs) This fixes the race condition with very small graphs where the main thread happens to start a new graph while the workers are just about to exit from barriers. * threadpool: use relaxed order for chunk sync Full memory barrier is an overkill for this since each thread works on different chunk * threadpool: remove abort_callback from threadpool state * threadpool: better naming for thread/cpumask releated functions * threadpool: consistent use of int type for n_threads params * threadpool: add support for ggml_threadpool_params_default/init Also removes the need for explicit mask_specified param. all-zero cpumask means use default (usually inherited) cpu affinity mask. * threadpool: move typedef into ggml.h * threadpool: fix apply_priority() function name * threadpool: fix swift wrapper errors due to n_threads int type cleanup * threadpool: enable --cpu-mask and other threadpool related options only if threadpool is enabled * threadpool: replace checks for compute_thread ret code with proper status check * threadpool: simplify threadpool init logic and fix main thread affinity application Most of the init code is now exactly the same between threadpool and openmp. * threadpool: update threadpool resume/pause function names * threadpool: enable openmp by default for now * threadpool: don't forget to free workers state when omp is enabled * threadpool: avoid updating process priority on the platforms that do not require it On Windows we need to change overall process priority class in order to set thread priorities, but on Linux, Mac, etc we do not need to touch the overall process settings. * threadpool: update calling thread prio and affinity only at start/resume This avoids extra syscalls for each graph_compute() * llama-bench: turn threadpool params into vectors, add output headers, etc * llama-bench: add support for cool off between tests --delay This helps for long running tests on platforms that are thermally limited (phones, laptops, etc). --delay (disabled by default) introduces the sleep for N seconds before starting each test. * threadpool: move process priority setting into the apps (bench and cli) This avoids changing the overall process priority on Windows for the apps that use ggml/llama.cpp directy. * threadpool: move all pause/resume logic into ggml * threadpool: futher api cleanup and prep for future refactoring All threadpool related functions and structs use ggml_threadpool prefix. * threadpool: minor indent fixes * threadpool: improve setprioty error message * Update examples/llama-bench/llama-bench.cpp Co-authored-by: slaren <slarengh@gmail.com> * threadpool: fix indent in set_threadpool call * use int32_t for n_thread type in public llama.cpp API * threadpool: use _new and _free instead of _create and _release * fix two more public APIs to use int32_t for n_threads * build: set _GNU_SOURCE for Adroid --------- Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com> Co-authored-by: fmz <quic_fzaghlou@quic.com> Co-authored-by: Max Krasnyansky <max.krasnyansky@gmail.com> Co-authored-by: slaren <slarengh@gmail.com>	2024-08-30 01:20:53 +02:00
Georgi Gerganov	20f1789dfb	vulkan : fix build (#0) ... ggml-ci	2024-08-27 22:41:27 +03:00
Georgi Gerganov	231cff5f6f	sync : ggml	2024-08-27 22:41:27 +03:00
slaren	7d787ed96c	ggml : do not crash when quantizing q4_x_x with an imatrix (#9192)	2024-08-26 19:44:43 +02:00
Georgi Gerganov	06658ad7c3	metal : separate scale and mask from QKT in FA kernel (#9189) ... * metal : separate scale and mask from QKT in FA kernel * metal : ne01 check no longer necessary * metal : keep data in local memory	2024-08-26 18:31:02 +03:00
Georgi Gerganov	fc18425b6a	ggml : add SSM Metal kernels (#8546) ... * ggml : add ggml_ssm_conv metal impl * ggml : add ssm_scan metal impl ggml-ci	2024-08-26 17:55:36 +03:00
slaren	0c41e03ceb	metal : gemma2 flash attention support (#9159)	2024-08-26 11:08:59 +02:00
Johannes Gäßler	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
Akarshan Biswas	11b84eb457	[SYCL] Add a space to supress a cmake warning (#9133)	2024-08-22 22:09:47 +08:00
luoyu-intel	1731d4238f	[SYCL] Add oneDNN primitive support (#9091) ... * add onednn * add sycl_f16 * add dnnl stream * add engine map * use dnnl for intel only * use fp16fp16fp16 * update doc	2024-08-22 12:50:10 +08:00
compilade	a1631e53f6	llama : simplify Mamba with advanced batch splits (#8526) ... * llama : advanced batch splits This includes equal-sequence-length batch splits which are useful to simplify recurrent model operators. * llama : always make recurrent state slots contiguous * ggml : simplify mamba operators * llama : fix integer signedness mixing * llama : logits_all has priority over batch->logits Otherwise, the server embeddings tests failed. This was likely an existing problem but was only detected here because of an additional assertion. * llama : apply suggestions Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * llama : fix t5 segfault * llama : fix Mamba session save and restore * llama : minor cosmetic changes * llama : rename llama_reorder_outputs to llama_output_reorder Also move it closer to llama_output_reserve. * llama : fix pooled embeddings when using batches with equal_seqs * minor : add struct members for clarity ggml-ci * llama : fix T5 segfault again * llama : fix Mamba pooled embeddings with multiple sequences Until the pooled embeddings are refactored to allow splitting across ubatches for causal embeddings, recurrent models can only process a single sequence per ubatch when calculating pooled embeddings. * llama : add llama_model_is_recurrent to simplify figuring that out This will make it easier to more cleanly support RWKV-v6 and Mamba-2. * llama : fix simple splits when the batch contains embeddings --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-08-21 17:58:11 -04:00
Changyeon Kim	2f3c1466ff	llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984) ... * llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. - The CLIP model now prioritizes the Vulkan backend over the CPU when vulkan available. - A GGML_OP_ACC shader has been added. - The encoding performance of the CLIP model improved from 4.2s on the CPU to 0.9s on the GPU. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * fix-up coding style. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * Fix-up the missing initial parameter to resolve the compilation warning. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * [fix] Add missing parameters. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * [fix] Use nb1 and nb2 for dst. Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> * Fix check results ggml_acc call --------- Signed-off-by: Changyeon Kim <cyzero.kim@samsung.com> Co-authored-by: 0cc4m <picard12@live.de>	2024-08-20 21:00:00 +02:00
Meng, Hengyu	50addec9a5	[SYCL] fallback mmvq (#9088) ... * fallback mmvq to mul_mat * mmvq in cuda path * Update ggml/src/ggml-sycl.cpp Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@codeplay.com> --------- Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@codeplay.com>	2024-08-20 23:50:17 +08:00
zhentaoyu	4f8d19ff17	[SYCL] Fix SYCL im2col and convert Overflow with Large Dims (#9052) ... * sycl: fix im2col overflow and sync with cuda Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix convert overflow Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix convert and dequantize Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix ib in dmmv Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl:refine convert Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: move downsample global_range into common Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: add im2col and convert test cases Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: make new cases only in sycl Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: comment new test_cases for only local testing Signed-off-by: zhentaoyu <zhentao.yu@intel.com> --------- Signed-off-by: zhentaoyu <zhentao.yu@intel.com>	2024-08-20 23:06:51 +08:00
Radoslav Gerganov	1b6ff90ff8	rpc : print error message when failed to connect endpoint (#9042)	2024-08-19 10:11:45 +03:00
Radoslav Gerganov	18eaf29f4c	rpc : prevent crashes on invalid input (#9040) ... Add more checks which prevent RPC server from crashing if invalid input is received from client	2024-08-19 10:10:21 +03:00