summaryrefslogtreecommitdiff
path: root/llama.cpp
AgeCommit message (Collapse)Author
2024-04-26Reset schedule earlier to allow overlap with ggml graph computation on ↵agray3
device (#6933) * Reset schedule earlier to allow overlap with graph computation on device
2024-04-26quantize: add imatrix and dataset metadata in GGUF (#6658)Pierrick Hymbert
* imatrix: save the dataset file used in the output file * llama: support kv overrides type string string * common: factorize KV Overrides parsing between common and server * quantize: add imatrix n entries and dataset KV metadata quantize: factorize KV Overrides parsing between common #6656 * llama: remove kv override str_value initialization as it does not compile on some toolchain * quantize: add imatrix m_last_call as `quantize.imatrix.chunks_count` * quantize: add imatrix filename in KV * llama: add llama_model_kv_override_free * common: add llama_model_kv_override_free common: free kv override if used after model loading * llama: finally move the string KV override value to the stack * llama : minor * no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators. Co-authored-by: slaren <slarengh@gmail.com> * kv override: ensure string termination --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: slaren <slarengh@gmail.com>
2024-04-26add basic tensor data validation function (#6884)slaren
* add basic tensor data validation function * add --check-tensors command line argument tensor validation is disabled by default and can be enabled by adding `--check-tensors` to the command line arguments. quantize always validates tensors.
2024-04-25cmake : restore LLAMA_LLAMAFILE_DEFAULTGeorgi Gerganov
2024-04-25llama : synchronize before get/set session data (#6911)slaren
2024-04-25llama : check that all the tensor data is in the model file (#6885)slaren
* llama : check that all the tensor data is in the model file * also check for unsigned overflow
2024-04-25tests : minor bash stuff (#6902)Georgi Gerganov
* tests : minor bash stuff ggml-ci * llama : fix build ggml-ci * tests : fix CUR_DIR -> ROOT_DIR ggml-ci * tests : fix fname ggml-ci
2024-04-25quantize : add '--keep-split' to quantize model into shards (#6688)jiez
* Implement '--keep-split' to quantize model into several shards * Add test script * Update examples/quantize/quantize.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Split model correctly even if tensor id is out-of-order * Update llama_model_quantize_params * Fix preci failures --------- Co-authored-by: z5269887 <z5269887@unsw.edu.au> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-24llama : add llama_get_pooling_type function (#6862)Douglas Hanley
* add llama_get_pooling_type function * fix argument name, move with ctx funcs
2024-04-24Server: fix seed for multiple slots (#6835)Johannes Gäßler
* Server: add tests for consistent results * sampling: separate rng per sampling context
2024-04-24llama : add phi 3 chat template (#6857)Tristan Druyen
* Add phi 3 chat template & tests * test : fix chat template result --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-24llama : add phi3 support (#6852)liuwei-git
* add explicit phi3 support * add explicit phi3 support * remove unused code * convert : add BOS token * llama : match EOT token <|end|> * llama : minor / style * llama : tabs -> spaces * convert : fix lint checks --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-22llama : fix typo in <|im_end|> token text (#6745)Georgi Gerganov
2024-04-21llama : add option to render special/control tokens (#6807)Georgi Gerganov
* make : fix common dep on llama.h * llama : add option to render special tokens * readme : add API change notice ggml-ci * swift : fix build
2024-04-21llama : add llama-3 chat template (#6751)Wouter
* Added llama-3 chat template * Update llama.cpp Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com> * Update llama.cpp Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com> * Update tests/test-chat-template.cpp Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com> * Added EOS stop sequence according to https://github.com/ggerganov/llama.cpp/pull/6751#issuecomment-2065602862 * Removed adding of BOS token before first message * Removed bos token from expected output from llama-3 * Update tests/test-chat-template.cpp Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> * Update tests/test-chat-template.cpp Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> * Added <|end_of_text|> as another stop token * Reverted last change of adding the end_of_text stop word for llama 3 --------- Co-authored-by: Wouter Tichelaar <tichelaarw@spar.net> Co-authored-by: Samuel Tallet <36248671+SamuelTallet@users.noreply.github.com> Co-authored-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-21llama : support Llama 3 HF conversion (#6745)Pedro Cuenca
* Support Llama 3 conversion The tokenizer is BPE. * style * Accept suggestion Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com> * llama : add llama_token_is_eog() ggml-ci * llama : auto-detect more EOT tokens when missing in KV data * convert : replacing EOS token is a hack * llama : fix codegemma EOT token + add TODOs * llama : fix model type string for 8B model --------- Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-19Implement the OLMo architecture (#6741)nopperl
* implement olmo architecture * remove unused variable * remove unused moe branch * remove check for weight * remove superfluous moe, bias and rope tensors * clarified comment * fix clamp_kqv setting * remove obsolete parameter name filter
2024-04-18ggml : group all experts in a single ggml_mul_mat_id (#6505)slaren
* ggml : group all experts in a single ggml_mul_mat_id cuda : improve mmid row copy * cuda : fix bin bcast with non-cont src0 * test-backend-ops : only run all mul mat tests for base types * llama : disable moe offloading with SYCL --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-18Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)Ren Xuancheng
2024-04-18llama : fix compatibility with old 2 expert models (#6735)slaren
2024-04-16llama : make general.name optional (#6709)Georgi Gerganov
2024-04-16llama : add StableLM2 12B (#6635)Ashish
* StableLM2 12B support for huggingface -> GGUF * StableLM12 tensormapping and constants * StableLM-2-12b model support * fix * Added 12B support * Removed autoformatting; resolved bug where model_arch was not selecting StableLM2 * Formatting * Do QK norm stacking in model conversion step * Converge StableLM and StableLM2 code to simplify graph construction * Fix accidental removal * Removed warnings * Revert formatter * Move QK norm stack to private function so it's easier to read * refactor stablelm graph builder to support 1.6, 3b and 12b more efficiently * Proper check for None type for new_name to avoid crash; formatting; revert change to base class `write_tensors()` * Format * Formatting * format Co-authored-by: compilade <git@compilade.net> * Fix incorrect check for K norm * space after commas; Keep indentation multiple of 4 spaces * Flake8 format * Removed unnecessary conditional branches * Removed unused comment * Fixed incorrect tensor passing * Format --------- Co-authored-by: compilade <git@compilade.net>
2024-04-16llama : add qwen2moe (#6074)Shijie
* support qwen2moe * fix-review * metal : support unary ops for nelements % 4 != 0 * metal : require contiguousness for float4 unary kernels * metal : require contiguousness for float4 unary kernels (cont) * fix-review * names : for brevity "SHARED_EXP" -> "SHEXP" * llama : reuse build_moe_ffn() * llama : add model type name --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-16gguf : add special tokens metadata for FIM/Infill (#6689)Daniel Bevenius
This commit adds special token metadata for Fill-In-the-Middle (FIM)/Infill to the GGUF model. The motivation for this is that currently there is support for CodeLlama but other models exist now like CodeGemma, but the different models use different token ids for the special tokens and this commit allows for supporting multiple models. Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-04-15llama : fix restoring the number of outputs from state files (#6687)compilade
2024-04-14llama : add missing kv clear in llama_beam_search (#6664)David Renshaw
2024-04-14Add Command R chat template (#6650)Chao Jiang
* Add chat template for command-r model series * Fix indentation * Add chat template test for command-r models and update the implementation to trim whitespaces * Remove debug print
2024-04-13model: support arch `DbrxForCausalLM` (#6515)Pierrick Hymbert
* model: dbrx convert to gguf #6344 * llama: support dbrx #6344 * doc: dbrx: add the model as supported * scripts: get-wikitext-2 add unzip * llama: increase maximum experts allowed * llama: factorize moe graph implementation between grok, mixtral and dbrx --------- Co-authored-by: Megha Agarwal <16129366+megha95@users.noreply.github.com>
2024-04-12llama : add gguf_remove_key + remove split meta during quantize (#6591)jiez
* Remove split metadata when quantize model shards * Find metadata key by enum * Correct loop range for gguf_remove_key and code format * Free kv memory --------- Co-authored-by: z5269887 <z5269887@unsw.edu.au>
2024-04-12Correct free memory and total memory. (#6630)MasterYi1024
Co-authored-by: MasterYi <zouxiaoyi@kylinos.cn>
2024-04-11Optimization: eliminate addition of redundant stacks when advancing grammar. ↵Clint Herron
(#6616)
2024-04-11grammars: 1.5x faster inference w/ complex grammars (vector reserves / ↵Olivier Chafik
reuses) (#6609) * grammars: reserve rejects & next candidates * grammars: reuse new_stacks * grammars: fix missing sig change in llama.h * grammars: fix test (api changed) * grammars: update gbnf-validator.cpp * grammars: simpler syntax (no swap)
2024-04-11eval-callback: Example how to use eval callback for debugging (#6576)Pierrick Hymbert
* gguf-debug: Example how to use ggml callback for debugging * gguf-debug: no mutex, verify type, fix stride. * llama: cv eval: move cb eval field in common gpt_params * ggml_debug: use common gpt_params to pass cb eval. Fix get tensor SIGV random. * ggml_debug: ci: add tests * ggml_debug: EOL in CMakeLists.txt * ggml_debug: Remove unused param n_batch, no batching here * ggml_debug: fix trailing spaces * ggml_debug: fix trailing spaces * common: fix cb_eval and user data not initialized * ci: build revert label * ggml_debug: add main test label * doc: add a model: add a link to ggml-debug * ggml-debug: add to make toolchain * ggml-debug: tests add the main label * ggml-debug: ci add test curl label * common: allow the warmup to be disabled in llama_init_from_gpt_params * ci: add curl test * ggml-debug: better tensor type support * gitignore : ggml-debug * ggml-debug: printing also the sum of each tensor * ggml-debug: remove block size * eval-callback: renamed from ggml-debug * eval-callback: fix make toolchain --------- Co-authored-by: slaren <slarengh@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-10llama : add model types for mixtral (#6589)slaren
2024-04-09BERT tokenizer fixes (#6498)Jared Van Bortel
Key changes: * BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS * Nomic Embed conversion: pad vocab instead of slicing embedding tensor * llama_tokenize: handle added special tokens like HF does
2024-04-09llama : add Command R Plus support (#6491)Carolinabanana
* Add Command R Plus GGUF * Add Command R Plus GGUF * Loading works up to LayerNorm2D * Export new tensors in 1D so they are not quantized. * Fix embedding layer based on Noeda's example * Whitespace * Add line * Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda) * dranger003: Fix block index overflow in CUDA dequantizing. * Reverted blocked multiplication code as it still has issues and could affect other Llama arches * export norms as f32 * fix overflow issues during quant and other cleanup * Type convention Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * dranger003: Fix more int overflow during quant. --------- Co-authored-by: S <seast@Ss-Mac-Studio.local> Co-authored-by: S <s@example.com> Co-authored-by: slaren <slarengh@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-08llama : fix attention layer count sanity check (#6550)Georgi Gerganov
* llama : fix attention layer count sanity check * llama : fix parentheses in attention layer count sanity check There was otherwise a warning when compiling. --------- Co-authored-by: Francis Couture-Harpin <git@compilade.net>
2024-04-08quantize : fix precedence of cli args (#6541)Georgi Gerganov
2024-04-08llama : support negative ith in llama_get_ API (#6519)Rick G
* llama_sampling_sample with default args is more naively usable * Batches populated by either llama_batch_get_one or llama_batch_add work with default args * Previously get_one could use the default argument * Previously add should usually have used the last index where logits[idx] == true * This hopefully encourages the use of llama_batch_add * By giving expected results when using default arguments. * Adds "negative indexing" feature to llama_get_logits_ith and llama_get_embeddings_ith * Believed to work with any currently well behaved program * Default arg now works for both cases (previously would give strange results for add case) * Any non-negative number is unaffected and behaves as previously * Negative arguments were previously invalid. * Implemented as a special case of indexing as suggested by @compilade in https://github.com/ggerganov/llama.cpp/pull/6519 * Fixed mismatch type errors * cited in macOS CI tests * Missed in original updates based on PR feedback in https://github.com/ggerganov/llama.cpp/pull/6519
2024-04-08llama : save and restore kv cache for single seq id (#6341)Jan Boon
* llama : save and restore kv cache for single seq id * remove trailing whitespace * respond error in case there's no space in the kv cache * add kv seq save restore to test case * add --slot-save-path arg to enable save restore and restrict save location * Returning 0 for some cases, instead of asserting. * cleanup error cases * rename sequence state functions * rename state get set functions * add previous function names back in with DEPRECATED notice * update doc * adjust endpoints to preferred style * fix restoring zero cell count * handle seq rm return value * unused param * keep in the size check * fix return types * add server test case for slot save restore * cleanup * add cake * cleanup style * add special * removing a whole sequence never fails * move sequence state file functionality from server to llama to match session api and add version tags * catch exceptions on save as well * error log messages * check types for stricter restore * update server doc * readme : update API changes date * strict filename validation * move include, reject bom as well * also reject empty filename * reject whitespace and trailing dot --------- Co-authored-by: Martin Evans <martindevans@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-05gguf.py : add licence and version to gguf writer (#6504)Brian
2024-04-04examples : add GBNF validator program (#5948)Clint Herron
* Revising GBNF validator program to be much simpler. * Changing from streams to using cstdio * Adding final newline character.
2024-04-03llama : add SEA-LION support (#6448)bryanSwk
* initial commit for sealion support * add sealion support * minor fix * q/k ln and pos_embd only if required * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * minor : clear whitespaces --------- Co-authored-by: bryan <bryansiow@aisingapore.org> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-03Add OpenChat, Alpaca, Vicuna chat templates (#6397)kaizau
* Add openchat chat template * Add chat template test for openchat * Add chat template for vicuna * Add chat template for orca-vicuna * Add EOS for vicuna templates * Combine vicuna chat templates * Add tests for openchat and vicuna chat templates * Add chat template for alpaca * Add separate template name for vicuna-orca * Remove alpaca, match deepseek with jinja output * Regenerate chat template test with add_generation_prompt * Separate deepseek bos from system message * Match openchat template with jinja output * Remove BOS token from templates, unprefix openchat
2024-04-03ggml : mul_mat_id use the same tensor for all the experts (#6387)slaren
* ggml : update mul_mat_id to use the same tensor for all the experts * update cuda * minor * update metal * update test-backend-ops * fix cuda * Update ggml-metal.m Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * update convert.py * update convert-hf-to-gguf.py * update convert.py for mixtral hf models * Update convert-hf-to-gguf.py Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * cuda : support non-pow-2 number of experts * allow quantize to work for split and merged experts models in the same way * cleanup + disable mmap automatically with split tensors models * update imatrix * test-backend-ops : test qwen argsort * update grok model loading * llama : add merged experts tensors to the grok tensor map * minor * gguf : bump version * fix quantizing of merged experts * convert-hf-to-gguf.py : update grok (untested) * make linter happy * cuda/argsort : use shared memory instead of pool memory * convert : fix grok tensor names * metal : add support for non-pow-2 argsort * llama : more loader cleanup, better error checking * cuda : fix warning * llama : still use mmap for loading old models, but copy the data to a host buffer * add review note * llama : remove ffn tensor counting + add sanity check ggml-ci * convert : fix handling of n_experts == None ggml-ci * imatrix : fix ncall counters * llama : produce error if imatrix size does not match * quantize : terminate on errors + trace logs ggml-ci * metal : pad shared memory to 16 bytes --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-29Vulkan k-quant mmq and ggml-backend offload functionality (#6155)0cc4m
* Fix Vulkan no kv offload incoherence * Add k-quant mul mat mat shaders * Rework working buffer allocation, reduces vram use noticeably Clean up cpu assist code, replaced with ggml-backend offload function * Default to all dedicated GPUs * Add fallback for integrated GPUs if no dedicated GPUs are found * Add debug info which device is allocating memory * Fix Intel dequant issue Fix validation issue * Fix Vulkan GGML_OP_GET_ROWS implementation * Clean up merge artifacts * Remove Vulkan warning
2024-03-29[Model] Add support for xverse (#6301)hxer7963
* Support xverse model convert to gguf format. * 1. Convert xverse models to gguf; 2. Add LLM_ARCH_XVERSE inference in llama.cpp; 3. Add xverse item in Supported models in README.md; * * gguf-py: remove redundant logs * llama: remove the init_mapping_prefetch custom parameter * llama.cpp: Include the changes from #6122 to exclude the unused outputs of the last layers. * - Fix format issues - Remove duplicate set kqv_out to llm_build_kv * Update llama.cpp --------- Co-authored-by: willhe <willhe@xverse.cn> Co-authored-by: willhe <hexin@xverse.cn>
2024-03-29llama : remove redundant reshape in build_kv_store (#6369)Daniel Bevenius
* llama: remove redundant reshape in build_kv_store This commit removes the reshape of the V matrix in the build_kv_store. The motivation for this is that V matrix has the shape: ```console (gdb) p *v_cur $46 = {type = GGML_TYPE_F32, backend = GGML_BACKEND_TYPE_CPU, buffer = 0x0, ne = {4096, 512, 1, 1}, nb = {4, 16384, 8388608, 8388608}, op = GGML_OP_MUL_MAT, op_params = { 0 <repeats 16 times>}, flags = 0, grad = 0x0, src = {0xb496b0, 0x7ffef1c40950, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, perf_runs = 0, perf_cycles = 0, perf_time_us = 0, view_src = 0x0, view_offs = 0, data = 0x0, name = "Vcur-0", '\000' <repeats 57 times>, extra = 0x0, padding = "\000\000\000\000\000\000\000"} ``` And after reshaping this tensor we get: ```console gdb) p *ggml_reshape_2d(ctx, v_cur, n_embd_v_gqa, n_tokens) $44 = {type = GGML_TYPE_F32, backend = GGML_BACKEND_TYPE_CPU, buffer = 0x0, ne = {4096, 512, 1, 1}, nb = {4, 16384, 8388608, 8388608}, op = GGML_OP_RESHAPE, op_params = { 0 <repeats 16 times>}, flags = 0, grad = 0x0, src = {0x7ffef1c40e00, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, perf_runs = 0, perf_cycles = 0, perf_time_us = 0, view_src = 0x7ffef1c40e00, view_offs = 0, data = 0x0, name = "Vcur-0 (reshaped)", '\000' <repeats 46 times>, extra = 0x0, padding = "\000\000\000\000\000\000\000"} ``` I noticed that the `src` and `view_src` fields are different but that the dimensions are the same. From the code comment it seems like the reshape call is not needed and perhaps the above can motivate the removal of the reshape call. Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com> * llama : add assert --------- Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-28llama : fix command-r inference when omitting outputs (#6367)compilade
2024-03-26wpm : portable unicode tolower (#6305)Jared Van Bortel
Also use C locale for ispunct/isspace, and split unicode-data.cpp from unicode.cpp.
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-05 14:12:53 +0000