153 Commits

Author	SHA1	Message	Date
Molly Sophia	11d47057a5	Rwkv chat template fix (#10001) ... * llama: remove useless template matching for rwkv-world Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * converter: Add comment about the hack for rwkv models Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * Update src/llama.cpp Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> --------- Signed-off-by: Molly Sophia <mollysophia379@gmail.com> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>	2024-10-22 15:22:26 +02:00
Molly Sophia	4ff7fe1fb3	llama : add chat template for RWKV-World + fix EOT (#9968) ... * Add chat template for RWKV-World Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * RWKV: Fix the chat template not being used Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * RWKV v6: Set EOT token to ``\n\n`` Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * readme: add rwkv into supported model list Signed-off-by: Molly Sophia <mollysophia379@gmail.com> --------- Signed-off-by: Molly Sophia <mollysophia379@gmail.com>	2024-10-22 13:33:37 +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
Georgi Gerganov	55e47786e3	llama : default sampling changes + greedy update (#9897) ... * llama : deprecate softmax sampler + fix dist sampler ggml-ci * tests : replace macros with functions ggml-ci * sampling : change temperature sampler logic For t <= 0.0f, keep the max logit intact and set the rest to -inf * cont : no need for special "greedy" logic top-k == 1 is the same * tests : init prob correctly * llama : handle temp <= 0.0 in the temp_ext sampler too ggml-ci * cont : avoid extra loop in temperature sampler for sub-zero temp ggml-ci	2024-10-21 09:46:40 +03:00
Xuan Son Nguyen	cda0e4b648	llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) ... * refactor llama_batch_get_one * adapt all examples * fix simple.cpp * fix llama_bench * fix * fix context shifting * free batch before return * use common_batch_add, reuse llama_batch in loop * null terminated seq_id list * fix save-load-state example * fix perplexity * correct token pos in llama_batch_allocr	2024-10-18 23:18:01 +02:00
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
Daniel Bevenius	6f55bccbb8	llama : rename batch_all to batch (#8881) ... This commit addresses the TODO in the code to rename the `batch_all` parameter to `batch` in `llama_decode_internal`.	2024-10-18 01:41:51 +02:00
Georgi Gerganov	9f45fc1e99	llama : change warning to debug log	2024-10-17 23:27:42 +03:00
Georgi Gerganov	99bd4ac28c	llama : infill sampling handle very long tokens (#9924) ... * llama : infill sampling handle very long tokens ggml-ci * cont : better indices ggml-ci	2024-10-17 22:32:47 +03:00
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
Daniel Bevenius	9e04102448	llama : suppress conversion from 'size_t' to 'int' (#9046) ... * llama : suppress conversion from 'size_t' to 'int' This commit updates llm_tokenizer_spm.tokenize to suppress/remove the following warnings that are generated on Windows when using MSVC: ```console src\llama-vocab.cpp(211,1): warning C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data src\llama-vocab.cpp(517,1): warning C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data ``` This is done by adding a cast for the size_t returned from symbols.size(). I believe this is safe as it seems unlikely that symbols, which stores an entry for each UTF8 character, would become larger than INT_MAX. The motivation for this change is to reduce the number of warnings that are currently generated when building on Windows. * squash! llama : suppress conversion from 'size_t' to 'int' Move cast into for loop.	2024-10-16 20:34:28 +03:00
Molly Sophia	10433e8b45	llama : add tensor name for "result_norm" (#9907) ... Signed-off-by: Molly Sophia <mollysophia379@gmail.com>	2024-10-16 13:10:21 +03:00
Georgi Gerganov	755a9b2bf0	llama : add infill sampler (#9896) ... ggml-ci	2024-10-15 16:35:33 +03:00
MaggotHATE	fbc98b748e	sampling : add XTC sampler (#9742) ... * Initial XTC commit Adds XTC sampler, not activated by default, but recommended settings by default. * Cleanup * Simplified chances calculation To be more inline with the original implementation, chance is calculated once at the beginning. * First fixes by comments Still need to look into sorting * Fixed trailing backspaces * Fixed RNG to be reproduceable Thanks to @slaren for directions * Fixed forgotten header * Moved `min_keep` Moved from conditions to a simple check at the end. * Fixed broken randomization Thanks to @slaren for explanation * Swapped sorting for a custom algorithm Shifts tokens to remove the penalized ones, then puts the penalized at the back. Should make `min_keep` still viable. * Algorithm rework 1. Scan token from top till the first non-penalizable 2. Remove the last captured token (the least probable above threshold) 3. Shift all tokens to override the remaining penalizable 4. Penalize and put them at the the bottom. * Added XTC to `test-sampling` * Simplified algorithm and more tests * Updated info in common and args * Merged back lost commits in common and arg * Update dump info in common * Fixed incorrect min_keep check * Added XTC to README * Renamed parameters, fixed info and defaults * probability is at 0 by default, but XTC is included in sampling queue * threshold higher than 0.5 switches XTC off * Initial server support * Added XTC to server UIs * Fixed labels in old server UI * Made algorithm safer and more readable * Removed xtc_threshold_max * Fixed arg after update * Quick fixes by comments * Simplified algorithm since threshold_max is removed * Renamed random distribution * Fixed tests and outdated README * Small fixes	2024-10-15 12:54:55 +02:00
Georgi Gerganov	d4c19c0f5c	server : accept extra_context for the infill endpoint (#9874) ... * server : accept extra_context for the infill endpoint ggml-ci * server : update readme [no ci] * server : use repo-level FIM pattern if possible ggml-ci	2024-10-13 21:31:35 +03:00
Georgi Gerganov	11ac9800af	llama : improve infill support and special token detection (#9798) ... * llama : improve infill support ggml-ci * llama : add more FIM token strings ggml-ci * server : update prompt on slot restore (#9800) * gguf : deprecate old FIM token KVs	2024-10-12 08:21:51 +03:00
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
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
Xuan Son Nguyen	458367a906	server : better security control for public deployments (#9776) ... * server : more explicit endpoint access settings * protect /props endpoint * fix tests * update server docs * fix typo * fix tests	2024-10-08 13:27:04 +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
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
Georgi Gerganov	8c475b97b8	rerank : use [SEP] token instead of [BOS] (#9737) ... * rerank : use [SEP] token instead of [BOS] ggml-ci * common : sanity check for non-NULL tokens ggml-ci * ci : adjust rank score interval ggml-ci * ci : add shebang to run.sh ggml-ci	2024-10-05 15:55:04 +03:00
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
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
Xuan Son Nguyen	a39ab216aa	llama : reduce compile time and binary size (#9712) ... * llama : speed up compile time * fix build * fix build (2)	2024-10-02 15:49:55 +02:00
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	a90484c6d9	llama : print correct model type for Llama 3.2 1B and 3B	2024-10-01 11:42:01 +03:00
Georgi Gerganov	f4d2b8846a	llama : add reranking support (#9510) ... * py : add XLMRobertaForSequenceClassification [no ci] * py : fix scalar-tensor conversion [no ci] * py : fix position embeddings chop [no ci] * llama : read new cls tensors [no ci] * llama : add classigication head (wip) [no ci] * llama : add "rank" pooling type ggml-ci * server : add rerank endpoint ggml-ci * llama : aboud ggml_repeat during classification * rerank : cleanup + comments * server : accept /rerank endpoint in addition to /v1/rerank [no ci] * embedding : parse special tokens * jina : support v1 reranker * vocab : minor style ggml-ci * server : initiate tests for later ggml-ci * server : add docs * llama : add comment [no ci] * llama : fix uninitialized tensors * ci : add rerank tests ggml-ci * add reranking test * change test data * Update examples/server/server.cpp Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> * add `--reranking` argument * update server docs * llama : fix comment [no ci] ggml-ci --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>	2024-09-28 17:42:03 +03:00
Zhenwei Jin	6102037bbb	vocab : refactor tokenizer to reduce init overhead (#9449) ... * refactor tokenizer * llama : make llm_tokenizer more private ggml-ci * refactor tokenizer * refactor tokenizer * llama : make llm_tokenizer more private ggml-ci * remove unused files * remove unused fileds to avoid unused filed build error * avoid symbol link error * Update src/llama.cpp * Update src/llama.cpp --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-28 15:10:58 +03:00
nopperl	9a913110cf	llama : add support for Chameleon (#8543) ... * convert chameleon hf to gguf * add chameleon tokenizer tests * fix lint * implement chameleon graph * add swin norm param * return qk norm weights and biases to original format * implement swin norm * suppress image token output * rem tabs * add comment to conversion * fix ci * check for k norm separately * adapt to new lora implementation * fix layer input for swin norm * move swin_norm in gguf writer * add comment regarding special token regex in chameleon pre-tokenizer * Update src/llama.cpp Co-authored-by: compilade <git@compilade.net> * fix punctuation regex in chameleon pre-tokenizer (@compilade) Co-authored-by: compilade <git@compilade.net> * fix lint * trigger ci --------- Co-authored-by: compilade <git@compilade.net>	2024-09-28 15:08:43 +03:00
Gabe Goodhart	3d6bf6919f	llama : add IBM Granite MoE architecture (#9438) ... * feat(gguf-py): Add granitemoe architecture This includes the addition of new tensor names for the new moe layers. These may not be correct at this point due to the need for the hack in gguf_writer.py to double-check the length of the shape for these layers. Branch: GraniteMoE Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat(convert_hf_to_gguf): Add GraniteMoeModel GraniteMoe has the same configuration deltas as Granite Branch: GraniteMoE Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(granitemoe convert): Split the double-sized input layer into gate and up After a lot of staring and squinting, it's clear that the standard mixtral expert implementation is equivalent to the vectorized parallel experts in granite. The difference is that in granite, the w1 and w3 are concatenated into a single tensor "input_linear." Rather than reimplementing all of the math on the llama.cpp side, the much simpler route is to just split this tensor during conversion and follow the standard mixtral route. Branch: GraniteMoE Co-Authored-By: alex.brooks@ibm.com Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat(granitemoe): Implement granitemoe GraniteMoE follows the mixtral architecture (once the input_linear layers are split into gate_exps/up_exps). The main delta is the addition of the same four multipliers used in Granite. Branch: GraniteMoE Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * Typo fix in docstring Co-Authored-By: ggerganov@gmail.com Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(conversion): Simplify tensor name mapping in conversion Branch: GraniteMoE Co-Authored-By: git@compilade.net Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(convert): Remove unused tensor name mappings Branch: GraniteMoE Co-Authored-By: git@compilade.net Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(convert): Sanity check on merged FFN tensor sizes Branch: GraniteMoE Co-Authored-By: git@compilade.net Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Allow "output" layer in granite moe architecture (convert and cpp) Branch: GraniteMoE Co-Authored-By: git@compilade.net Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(granite): Add missing 'output' tensor for Granite This is a fix for the previous `granite` architecture PR. Recent snapshots have included this (`lm_head.weights`) as part of the architecture Branch: GraniteMoE Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-25 10:06:52 +03:00
Georgi Gerganov	31ac5834fe	llama : keep track of all EOG tokens in the vocab (#9609) ... ggml-ci	2024-09-24 10:16:06 +03:00
Georgi Gerganov	cea1486ecf	log : add CONT level for continuing previous log entry (#9610)	2024-09-24 10:15:35 +03:00
Georgi Gerganov	b0f27361f3	sampling : avoid expensive softmax during greedy sampling (#9605) ... * sampling : avoid expensive softmax during greedy sampling ggml-ci * speculative : fix default RNG seed + set sparams.n_probs * Update tests/test-sampling.cpp Co-authored-by: slaren <slarengh@gmail.com> * sampling : add clarifying comment [no ci] --------- Co-authored-by: slaren <slarengh@gmail.com>	2024-09-24 09:03:17 +03:00
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
Shankar	ecd5d6b65b	llama: remove redundant loop when constructing ubatch (#9574)	2024-09-22 04:30:34 +02:00
Daniel Bevenius	6443ddd985	llama : use reserve/emplace_back in sampler_sample (#9534) ... This commit updates the llama_sampler_sample function to use reserve and emplace_back for the vector of llama_token_data structs. The motivation for this change is to avoid the creation of n_vocab default-constructed llama_token_data structs which are then immediately overwritten.	2024-09-18 14:42:36 +03:00
Michael Podvitskiy	8344ef58f8	llama : fix n_vocab init for 'no_vocab' case (#9511) ... * llama: fixed n_vocab for `no_vocab` models * llama: updated error output for `llama_decode_internal` and `llama_encode_internal` * llama: log warning if there's no vocab_size in metadata * llama: correct vocab size for logging Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-17 13:18:22 +03:00
Yuri Khrustalev	503147a9f9	unicode : add <algorithm> (#9508)	2024-09-17 09:51:15 +03:00
Gabe Goodhart	0d2ec43833	llama : support IBM Granite architecture (#9412) ... * feat(gguf-py): Add Granite model and params to gguf-py Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat(convert_hf_to_gguf): Add registration and param setup for Granite Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat(llama.cpp): Add config parsing for Granite multiplier params Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat(llama.cpp): First pass at full port of granite deviations from llama Something is still not working right since the results are mostly terrible, but on occasion it's producing relevant results at this point, so _something_ is working. Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(llama.cpp): Determine granite language 3b instruct by vocab size Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(convert_hf_to_gguf): Use LlamaModel as base for GraniteModel The defaults in LlamaModel are needed for Granite as well Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(llama.cpp): Switch Granite param names to use _scale for consistency Other scalar multipliers are called *_scale, so this provides a more consistent naming convention. Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(convert_hf_to_gguf/gguf-py): _multiplier -> _scale The transformers names with _multiplier will now be converted to the _scale equivalent during conversion. Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(llama.cpp): Use separate switch clause for granite in llm_load_hparams Branch: GraniteLM Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>	2024-09-17 09:44:58 +03:00
Michael Podvitskiy	37f3a3810e	llama : add llama_n_head() (#9512)	2024-09-17 09:23:30 +03:00
Daniel Bevenius	acb2c32c33	llama : rename n_embed to n_embd in rwkv6_time_mix (#9504) ... This commit renames n_embed to n_embd in llm_build_rwkv6_time_mix. The motivation for this change is consistency with the other rwkv6 functions like build_rwkv6 (and other parts of the code base).	2024-09-16 14:07:13 +03:00
Shane A	0aadac10c7	llama : support OLMoE (#9462)	2024-09-16 09:47:37 +03:00
CarryFun	95ca85168b	llama : support MiniCPM3 (#9322) ... Co-authored-by: 范睿凯 <fanruikai@modelbest.cn>	2024-09-16 09:45:20 +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
Daniel Bevenius	befaf1197f	llama : make cell_id const in inp_s_mask block (#9470) ... This commit makes the cell_id variable const in the inp_s_mask block. The motivation for this change is consistency with the code in the inp_s_copy block.	2024-09-14 10:50:12 +03:00
Georgi Gerganov	0abc6a2c25	llama : llama_perf + option to disable timings during decode (#9355) ... * llama : llama_perf + option to disable timings during decode ggml-ci * common : add llama_arg * Update src/llama.cpp Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> * perf : separate functions in the API ggml-ci * perf : safer pointer handling + naming update ggml-ci * minor : better local var name * perf : abort on invalid sampler pointer ggml-ci --------- Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>	2024-09-13 09:53:38 +03:00
Gilad S.	bd35cb0ae3	feat: remove a sampler from a chain (#9445) ... * feat: remove a sampler from a chain * fix: return removed sampler * fix: safer casting	2024-09-13 03:54:49 +02:00