summaryrefslogtreecommitdiff
path: root/tests
AgeCommit message (Collapse)Author
2024-04-30ggml : add Flash Attention (#5021)Georgi Gerganov
* ggml : add ggml_flash_attn_ext API * ggml : fix GQA support in ggml_flash_attn_ext * ggml : online attention (CPU) * metal : initial implementation * metal : f16 precision * metal : reduce branches * metal : specialize for head size * wip : 8 rows per simd group * wip : 4 rows per simd group * wip : template for rows per warp * metal : parallelize across KV size * metal : parallel reduce across heads * metal : efficient flash_attn_f16 implementation * metal : avoid redundant loads of the attention * metal : scale and mask in matrix form * metal : fix comment * llama : avoid ggml_cast, use F32 query * metal : add parallel reduce version (disabled) * metal : move output into local memory + optimize - the result from each simdgroup now stays in the registers - significantly reduced SRAM usage - more efficient skipping of -INF blocks - avoid simdgroup barrier in hot loop - add comments * metal : add tests, fix scaling, support C > 32 * metal : improve precision * ggml : fix f16 mad * metal : minor * metal : support Q > 8 * tests : add ATTN tests * metal : disable buffer allocation logs * tests : more * metal : faster inner loop for C == 32 * metal : fix array initialization * tests : ifdef * ggml : switch to padded F16 mask for ggml_soft_max, ggml_flash_attn_ext * ggml : fix ggml_soft_max mask requirement * cuda : fix soft_max to use correct mask size * cuda : add flash_attn kernel (wip) * metal : optimize softmax for C > 32 * metal : optimize softmax * tests : minor fix * cuda : avoid zeroing fragments * tests : update dims * cuda : fix __hisinf() result check * cuda : avoid warp_reduce for smax * cuda : use int instead of int64_t Noticeably improves performance (thanks to Johannes) * cuda : make loops use the same loop values Thanks Johannes again for the tip * cuda : unroll some of the loops * cuda : avoid __hisinf branches * cuda : use half2 in softmax * cuda : switch to 1 warp for bs > 16 * cuda : speed-up reduce part of the kernel * cuda : unroll Q*K^T loop * cuda : fix -INF block check * cuda : simplify softmax * cuda : fix matrix names * cuda : minor * llama : adapt to F16 KQ_pos * llama : adapt new models to F16 KQ_mask * ggml : fix F16 store (ARM NEON) * llama : fix type of KQ_mask and KQ_pos * ggml : fix CPU soft_max * tests : add hs=256 * cuda : fix build * metal : improve perf via smaller int registers * cuda : adapt soft_max to F16 mask and pos * CUDA: faster FlashAttention, kernel for bs == 1 * 16 cols for Phi-2 * no vec for hs, no hs==256 ncols==32 for Volta * adjust kernel selection logic * 4 warps, 256 stride for all D * no ncols == 64 * Multiple parallel blocks for batch size 1 * fix compile warnings * fix excessive KQ_b loads * fix cmake build * fix KV cache padding, NaN from INFINITY (#6438) * llama : flash_attn cparam + fix defrag * server: support flash_attn param * server: bench: enable flash_attn param * CUDA: refactor host code, dyn. par. blocks * fix flash_attn_vec_f16 race condition * flush softmax exp below threshold to 0 * store temp KQ in registers * Calculate KQ as FP32 if KQV has GGML_PREC_F32 * Add __hgt2_mask implementation for CUDA 11 * fix KQ FP32 precision fpr parallel_blocks > 1 * llama-bench : add -fa,--flash-attn arg * metal : add BS=1 kernel for flash attention (#6508) * metal : add BS=1 kernel for flash attention (wip) * metal : support more than 1 warps * metal : opts * metal : opt * metal : switch to parallel reduce * metal : reduce registers * metal : simplify * metal : initial FA vec kernel * metal : use F32 attention accumulators * batched-bench : add fattn arg * llama : simplify llama_build_kv_store ggml-ci * llama : adapt build_olmo to changes * ggml : fix arm fp16 store on windows * metal : clean-up * metal : clean-up kernel code * metal : minor * tests : remove benchmarks ggml-ci * ggml : fix avx512 const correctness ggml-ci * ggml : fix soft_max with bias on CPU ggml-ci * common : print --flash-attn in help * ggml : fix num dimensions in ggml_flash_attn_ext * llama : force disable flash attention for incompatible models * ggml : ggml_soft_max support F16/F32 mask/pos ggml-ci * cuda : uint -> uint32_t * cuda : "constexpr dim3" -> "const dim3" ggml-ci * cuda : try to fix __hgt2_mask ggml-ci * ggml : add TODO's for F16/F32 mask/pos support in other backends * llama : replace bool need_kq_pos with use_alibi * llama : prep ALiBi support for BERT models ggml-ci * llama : fix n_batch requirements ggml-ci * cont * server : add help for --flash-attn arg * llama : disable FA for AMD * tests : remove TMP_ATTN_BENCH ggml-ci * llama : support save/load state with FA enabled ggml-ci * ci : add CUDA save-load-state tests ggml-ci * llama : llama_kv_cache_clear zeroes data + fix save-load seq ggml-ci * llama : fix copy-paste errors, add TODO * llama : disallow incompatible states * llama : update llama_state_get_size after v_trans field * metal : remove tmp log * llama : add static reminder for llama_state_get_size * metal : fix max nsg ggml-ci * ci : fix arg order ggml-ci --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de> Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-04-29Extending grammar integration tests (#6644)Clint Herron
* Cleaning up integration tests to share code between tests and make it simpler to add new tests. * Add tests around quantifiers to ensure both matching and non-matching compliance. * Add slightly more complex grammar with quantifiers to test references with quantifiers. * Fixing build when C++17 is not present. * Separating test calls to give more helpful stack traces on failure. Adding verbose messages to give visibility for what is being tested. * Adding quotes around strings to explicitly show whitespace * Removing trailing whitespace. * Implementing suggestions from @ochafik -- grammars and test strings now print and flush before tests to aid in debugging segfaults and whatnot. * Cleaning up forgotten symbols. Modifying simple test to use test harness. Added comments for more verbose descriptions of what each test is accomplishing. * Unicode symbol modifications to hopefully make log easier to parse visually.
2024-04-29llama : fix BPE pre-tokenization (#6920)Georgi Gerganov
* merged the changes from deepseeker models to main branch * Moved regex patterns to unicode.cpp and updated unicode.h * Moved header files * Resolved issues * added and refactored unicode_regex_split and related functions * Updated/merged the deepseek coder pr * Refactored code * Adding unicode regex mappings * Adding unicode regex function * Added needed functionality, testing remains * Fixed issues * Fixed issue with gpt2 regex custom preprocessor * unicode : fix? unicode_wstring_to_utf8 * lint : fix whitespaces * tests : add tokenizer tests for numbers * unicode : remove redundant headers * tests : remove and rename tokenizer test scripts * tests : add sample usage * gguf-py : reader prints warnings on duplicate keys * llama : towards llama3 tokenization support (wip) * unicode : shot in the dark to fix tests on Windows * unicode : first try custom implementations * convert : add "tokenizer.ggml.pre" GGUF KV (wip) * llama : use new pre-tokenizer type * convert : fix pre-tokenizer type writing * lint : fix * make : add test-tokenizer-0-llama-v3 * wip * models : add llama v3 vocab file * llama : adapt punctuation regex + add llama 3 regex * minor * unicode : set bomb * unicode : set bomb * unicode : always use std::wregex * unicode : support \p{N}, \p{L} and \p{P} natively * unicode : try fix windows * unicode : category support via std::regex * unicode : clean-up * unicode : simplify * convert : add convert-hf-to-gguf-update.py ggml-ci * lint : update * convert : add falcon ggml-ci * unicode : normalize signatures * lint : fix * lint : fix * convert : remove unused functions * convert : add comments * convert : exercise contractions ggml-ci * lint : fix * cmake : refactor test targets * tests : refactor vocab tests ggml-ci * tests : add more vocabs and tests ggml-ci * unicode : cleanup * scripts : ignore new update script in check-requirements.sh * models : add phi-3, mpt, gpt-2, starcoder * tests : disable obsolete ggml-ci * tests : use faster bpe test ggml-ci * llama : more prominent warning for old BPE models * tests : disable test-tokenizer-1-bpe due to slowness ggml-ci --------- Co-authored-by: Jaggzh <jaggz.h@gmail.com> Co-authored-by: Kazim Abrar Mahi <kazimabrarmahi135@gmail.com>
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>
2024-04-21llama : 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>
2024-04-18ggml : 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>
2024-04-16llama : 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>
2024-04-15`main`: add --json-schema / -j flag (#6659)Olivier Chafik
* main: add --json-schema / -j * json: move json-schema-to-grammar to common lib * json: fix zig build
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
2024-04-12JSON schema conversion: ⚡️ faster repetitions, min/maxLength for ↵Olivier Chafik
strings, cap number length (#6555) * json: rename python schema converter to make import easier * server: skip null json_schema / grammar fields * json: deps management for primitive rules (+ allow null values) * json: optimize repetitions for minItems/maxItems and regexps: `a{,3}` goes from `"a"? "a"? "a"?` (explosive combos) to `(a (a (a)?)?)?` * grammars: add troubleshooting section to readme * json: cap length of numbers to 15 digits before/after decimal point (avoids infinite gen, e.g. "one third" -> `0.333333333333...`) * json: unify all repetition code (w/ or w/o sep) * json: support string minLength/maxLength * server+json: update server/README w/ result_format * nits * json: fix type error w/ python 3.8 * json: fix server/README (json_schema in /completion vs. result_format in /v1/chat/completions) * json: simplify DOT `{"type": "string", "pattern": "^.$"}` * json: remove recursion in opt_repetitions (avoids Python stack overflow) * json: rm dead code * json: rm useless assert & ggml.h import
2024-04-12metal : unify mul_mv_id kernels (#6556)slaren
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)
2024-04-06Tests: Added integration tests for GBNF parser (#6472)Clint Herron
* Added integration tests for GBNF parser to validate correctness of parsing, as well as correctness of string matching. Intended for use to pin behavior while working on performance improvements. * Fixing whitespace errors and cleaning error message alert to be clearer. * Removing hacky include to llama.cpp from grammar integration test now that needed functions are available via internal API. * Comment cleanup. * Reorganizing tests for readability. * Cleaning up debug message to make a bit more sense.
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>
2024-03-26IQ1_M: 1.75 bpw quantization (#6302)Kawrakow
* iq1_m: basics * iq1_m: basics-2 * iq1_m: CUDA dequantize works Very 1st shot I get PPL = 9.76 for LLaMA-v2-7B. * iq1_m: separate shifts for each group of 8 in a block We get PPL(LLaMA-v2-7B ) = 9.2810 PPL(LLaMA-v2-13B) = 6.8105 Not bad, but slightly higher than sqrt(PPL(IQ1_S) * PPL(IQ2_XXS)) which is the expected outcome given that IQ1_M is halfway between IQ1_S and IQ2_XXS in terms of bpw. From this, we would expect PPL = 9.14 for LLaMA-v2-7B PPL = 6.63 for LLaMA-v2-13B * iq1_m: go to 3-bit scales There is slight increase in PPL, but the 0.0625 bpw reduction in size is totally worth it. We now have PPL(LLaMA-v2-7B ) = 9.4469 at 1.96 bpw PPL(LLaMA-v2-13B) = 6.8717 at 1.93 bpw PPL(LLaMA-v2-70B) = 4.8568 at 1.85 bpw * iq1_m: scalar dot product * iq1_m: AVX2 dot product * iq1_m: very slightly faster AVX2 dot product * iq1_m: ARM_NEON dot product Works, but very slow (10.5 t/s) * iq1_m: Metal - dequantize works, dot product does not * iq1_m: Metal now works About the same performance as iq1_s. * iq1_m: minor * iq1_m: checking pure iq1_m quantization It is pretty bad: PPL(LLaMA-v2-7B) = 34 if we quantize output.weight with Q4_K. * iiq1_m: slightly faster ARM_NEON dot product 10.5 t/s -> 11.65 t/s * iq1_m: faster ARM_NEON dot product 11.65 t/s -> 14.9 t/s * iq1_m: another minor ARM_NEON dot product improvement 14.9 -> 15.0 t/s * iq1_m: small PPL improvement via super-block scale adjustment After quantizing block scales redo the super-block scale fit. PPL(LLaMA-v2-7B ) = 9.3346 PPL(LLaMA-v2-13B) = 6.8419 PPL(LLaMA-v2-70B) = 4.8294 PPL(Mistral-7B ) = 8.1624 * iq1_m: adapt to CUDA refactoring * iq1_m: remove unused variable We have progressed to warnings being errors. * iq1_m: add to backend-ops tests * iq1_m: fix Windows ARM * iq1_m: use common definition of iq1m_scale_t * cuda: assert -> NO_DEVICE_CODE * iq1_M: PR comments --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-25tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303)Kawrakow
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-22tests : conditional python & node json schema tests (#6207)Olivier Chafik
* json: only attempt python & node schema conversion tests if their bins are present Tests introduced in https://github.com/ggerganov/llama.cpp/pull/5978 disabled in https://github.com/ggerganov/llama.cpp/pull/6198 * json: orange warnings when tests skipped * json: ensure py/js schema conv tested on ubuntu-focal-make * json: print env vars in test
2024-03-22json-schema-to-grammar : fix order of props + non-str const/enum (#6232)Olivier Chafik
* json: ordered json in server/schema converter to respect orig order * json: ws nits * json: support non-string const / enums
2024-03-22metal : pad n_ctx by 32 (#6177)Georgi Gerganov
* metal : require ne00 >= 128 for mat-mat kernels ggml-ci * llama : pad n_ctx by 32 ggml-ci
2024-03-21tests : disable system() calls (#6198)Georgi Gerganov
ggml-ci
2024-03-21json-schema-to-grammar improvements (+ added to server) (#5978)Olivier Chafik
* json: fix arrays (disallow `[,1]`) * json: support tuple types (`[number, string]`) * json: support additionalProperties (`{[k: string]: [string,number][]}`) * json: support required / optional properties * json: add support for pattern * json: resolve $ref (and support https schema urls) * json: fix $ref resolution * join: support union types (mostly for nullable types I think) * json: support allOf + nested anyOf * json: support any (`{}` or `{type: object}`) * json: fix merge * json: temp fix for escapes * json: spaces in output and unrestricted output spaces * json: add typings * json:fix typo * Create ts-type-to-grammar.sh * json: fix _format_literal (json.dumps already escapes quotes) * json: merge lit sequences and handle negatives {"type": "string", "pattern": "^({\"question\": \"[^\"]+\", \"response\": \"[^\"]+\"}\\n)+$"} * json: handle pattern repetitions * Update json-schema-to-grammar.mjs * Create regex-to-grammar.py * json: extract repeated regexp patterns to subrule * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * json: handle schema from pydantic Optional fields * Update json-schema-to-grammar.py * Update json-schema-to-grammar.py * Update ts-type-to-grammar.sh * Update ts-type-to-grammar.sh * json: simplify nullable fields handling * json: accept duplicate identical rules * json: revert space to 1 at most * json: reuse regexp pattern subrules * json: handle uuid string format * json: fix literal escapes * json: add --allow-fetch * json: simplify range escapes * json: support negative ranges in patterns * Delete commit.txt * json: custom regex parser, adds dot support & JS-portable * json: rm trailing spaces * Update json-schema-to-grammar.mjs * json: updated server & chat `( cd examples/server && ./deps.sh )` * json: port fixes from mjs to python * Update ts-type-to-grammar.sh * json: support prefixItems alongside array items * json: add date format + fix uuid * json: add date, time, date-time formats * json: preserve order of props from TS defs * json: port schema converter to C++, wire in ./server * json: nits * Update json-schema-to-grammar.cpp * Update json-schema-to-grammar.cpp * Update json-schema-to-grammar.cpp * json: fix mjs implementation + align outputs * Update json-schema-to-grammar.mjs.hpp * json: test C++, JS & Python versions * json: nits + regen deps * json: cleanup test * json: revert from c++17 to 11 * json: nit fixes * json: dirty include for test * json: fix zig build * json: pass static command to std::system in tests (fixed temp files) * json: fix top-level $refs * json: don't use c++20 designated initializers * nit * json: basic support for reserved names `{number:{number:{root:number}}}` * Revamp test cmake to allow args (WORKING_DIRECTORY needed for JSON test) * json: re-ran server deps.sh * json: simplify test * json: support mix of additional props & required/optional * json: add tests for some expected failures * json: fix type=const in c++, add failure expectations for non-str const&enum * json: test (& simplify output of) empty schema * json: check parsing in test + fix value & string refs * json: add server tests for OAI JSON response_format * json: test/fix top-level anyOf * json: improve grammar parsing failures * json: test/fix additional props corner cases * json: fix string patterns (was missing quotes) * json: ws nit * json: fix json handling in server when there's no response_format * json: catch schema conversion errors in server * json: don't complain about unknown format type in server if unset * json: cleaner build of test * json: create examples/json-schema-pydantic-example.py * json: fix date pattern * json: move json.hpp & json-schema-to-grammar.{cpp,h} to common * json: indent 4 spaces * json: fix naming of top-level c++ function (+ drop unused one) * json: avoid using namespace std * json: fix zig build * Update server.feature * json: iostream -> fprintf * json: space before & refs for consistency * json: nits
2024-03-15llama : add Orion chat template (#6066)Xuan Son Nguyen
2024-03-13test-backend-ops : skip CPU backend by default (#6028)slaren
2024-03-11llama : refactor unicode stuff (#5992)Georgi Gerganov
* llama : refactor unicode stuff ggml-ci * unicode : names * make : fix c++ compiler * unicode : names * unicode : straighten tables * zig : fix build * unicode : put nfd normalization behind API ggml-ci * swift : fix build * unicode : add BOM * unicode : add <cstdint> ggml-ci * unicode : pass as cpts as const ref
2024-03-09ggml : remove old quantization functions (#5942)Georgi Gerganov
* ggml : remove old quantization functions ggml-ci * ggml : simplify ggml_quantize_chunk ggml-ci * ggml : restrict correctness ggml-ci * ggml : remove hist data from the quantization API ggml-ci * tests : remove hist usage in test-backend-ops ggml-ci * vulkan : remove hist and fix typo
2024-03-09tests : gitignore ggml-common.hGeorgi Gerganov
2024-03-04add some new ops, fix some operators and add batch operations to certain ↵leejet
operators. (ggml/747) * cuda: fix group_norm * cuda: add batch inference support for ggml_pad/ggml_upscale * add ggml_arrange * add ggml_timestep_embedding * update ggml_arange/ggml_timestep_embedding tests * cuda: fix im2col * add ggml_arange/ggml_timestep_embbeding support for metal backend * fix some bugs * fix some bugs * Update ggml.h Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml-cuda.cu Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml-metal.m Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml-metal.m Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml-metal.metal Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * modify according to the review comments * ggml : fix compile warnings + code style * ggml : normalize compute_forward calls + fix seg fault in debug * minor --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: slaren <slarengh@gmail.com>
2024-02-27IQ4_XS: a 4.25 bpw quantization (#5747)Kawrakow
* Try IQ4_NL with blocks of 64 - does not look good * iq4_xs: go to super-blocks of 256 and 6-bit scales for blocks of 32 * iq4_xs: CUDA works - 133.2 t/s * iq4_xs: AVX2 dot product * iq4_xs: ARM_NEON dot product * iq4_nl: Metal implementation As usual, Metal / Apple Silicon don't like my quants. * iq3_xs: minor fix * iq4_xs: shrink by using IQ3_S for attn_k and attn_q * iq4_xs: revert using IQ3_S for attn_k and attn_v PPL vs size is good, but CPU performance suffers: on M2 Max TG-128 drops to 21.7 t/s from 28.8, and on a Ryzen-7950X to 14.5 t/s from 15.8 t/s. On CUDA we have 135 t/s when using IQ3_S vs 133 t/s with pure IQ4_XS. * Fix CI * iq4_xs: Added forgotten check for 256 divisibility --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-26Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization ↵Kawrakow
range (#5721) * Adding IQ2_S and IQ2_M as a single cumulative commit * Update examples/quantize/quantize.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-25code : normalize enum names (#5697)Georgi Gerganov
* coda : normalize enum names ggml-ci * code : cont * code : cont
2024-02-24IQ3_S: a much better alternative to Q3_K (#5676)Kawrakow
* iq4_nl: squash commits for easier rebase * Basics (quantize, dequantize) * CUDA dequantize and dot product * Slightly faster CUDA dot product (120 t/s) * Switch to 6-bit scales * Scalar dot product * AVX2 dot product * ARM_NEON dot product * Works on metal, but still slow * Slightly better Metal dot product * Another small Metal improvement * Metal dot product is getting there * Faster CUDA dot product * Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided * Report the actual bpw * Add _xs mix that is 4.05 bpw for non-MoE models * Remove IQ4_XS for now, slightly adjust kvalues_iq4nl * AVX2 dot product uses Q8_0 instead of Q8_K * Add to test-backend-ops * Minor fix * Also use use Q5_K for attn_output in MoE models * Fixes after merging latest master * Switching to blocks of 32 * AVX2 for blocks of 32 * Scaler dot product for blocks of 32 * ARM_NEON dot product for blocks of 32 * Metal kernels for blocks of 32 * Slightly faster Metal kernels * Resurrecting iq3_xs After all the experimentation, nothing was better than this. * Minor PPL improvement via a block scale fudge factor * Minor improvement via 3 neighbours * iq3_xs: working scalar and AVX2 dot products * iq3_xs: ARM_NEON dot product - works but extremely slow (10 t/s) * iq3_xs: working Metal implementation * Adding IQ3_M - IQ3_XS mix with mostly Q4_K * iiq3_xs: a 3.4375 bpw variant * iq3_xs: make CUDA work for new version * iq3_xs: make scalar and AVX2 work for new version * iq3_s: make ARM_NEON work with new version * iq3_xs: make new version work on metal Performance is very similar to Q3_K_S * iq3_xs: tiny Metal speed improvement * iq3_xs: tiny Metal speed improvement * Fix stupid warning * Q3_K_XS now uses a mix of IQ3_XS and IQ3_XXS * iq3_xs: rename to iq3_s * iq3_s: make tests pass * Move Q3_K_XS mix to 3.25 bpw * Attempt to fix failing tests * Another attempt to fix the Windows builds * Attempt to fix ROCm * ROCm again * iq3_s: partial fix for QK_K = 64 * iq3_s: make it work on metal for QK_K = 64 Pleasent surprise: the coding was super-block size independent, so all it took was to delete some QK_K == 256 guards. * Will this fix ROCm? --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-22Add Gemma chat template (#5665)Xuan Son Nguyen
* add gemma chat template * gemma: only apply system_prompt on non-model message
2024-02-22server : fallback to chatml, add AlphaMonarch chat template (#5628)Xuan Son Nguyen
* server: fallback to chatml * add new chat template * server: add AlphaMonarch to test chat template * server: only check model template if there is no custom tmpl * remove TODO
2024-02-21IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)Kawrakow
* iq4_nl: squash commits for easier rebase * Basics (quantize, dequantize) * CUDA dequantize and dot product * Slightly faster CUDA dot product (120 t/s) * Switch to 6-bit scales * Scalar dot product * AVX2 dot product * ARM_NEON dot product * Works on metal, but still slow * Slightly better Metal dot product * Another small Metal improvement * Metal dot product is getting there * Faster CUDA dot product * Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided * Report the actual bpw * Add _xs mix that is 4.05 bpw for non-MoE models * Remove IQ4_XS for now, slightly adjust kvalues_iq4nl * AVX2 dot product uses Q8_0 instead of Q8_K * Add to test-backend-ops * Minor fix * Also use use Q5_K for attn_output in MoE models * Fixes after merging latest master * Switching to blocks of 32 * AVX2 for blocks of 32 * Scaler dot product for blocks of 32 * ARM_NEON dot product for blocks of 32 * Metal kernels for blocks of 32 * Slightly faster Metal kernels * iq4_nl: Fix after merging with master * iq4_nl: another fix after merging with master * Use IQ4_NL instead of Q4_K when using k-quants is not possible * Fix typo that makes several tests fail * It was the ggml_vdotq thing missed inside the brackets --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-19llama : add llama_chat_apply_template() (#5538)Xuan Son Nguyen
* llama: add llama_chat_apply_template * test-chat-template: remove dedundant vector * chat_template: do not use std::string for buffer * add clarification for llama_chat_apply_template * llama_chat_apply_template: add zephyr template * llama_chat_apply_template: correct docs * llama_chat_apply_template: use term "chat" everywhere * llama_chat_apply_template: change variable name to "tmpl"
2024-02-18ggml, common, examples, tests : fixed type arguments in printf (#5528)Herman Semenov
2024-02-181.5 bit quantization (#5453)Kawrakow
* iq1_s: WIP basics * iq1_s: CUDA is working * iq1_s: scalar CPU dot product * iq1_s: WIP AVX2 dot product - something is not right * Fix tests * Fix shadow warnings * Fix after merge with latest master * iq1_s: AVX2 finally works * iq1_s: ARM_NEON dot product. Works, but not very fast * iq1_s: better grid * iq1_s: use IQ2_XXS for attn_output At a cost of 0.04 extra bpw this gives a big improvement in PPL. * iq1_s: Metal basics Dequantize works, but not dot product * iq1_s: Metal works, but quite slow As usual, Apple Silicon does not like the code I write. * iq1_s: Tests * iq1_s: slightly faster dot product --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-17ggml : add ALiBi support for ggml_soft_max_ext (#5488)Georgi Gerganov
* ggml : avoid recomputing alibi slopes (CPU) * llama : reuse hparams.f_max_alibi_bias in all cases ggml-ci * ggml : support alibi bias in ggml_soft_max_ext (CPU + Metal) ggml-ci * ggml : handle all SRCs (do not break on first null) ggml-ci * tests : do not use slope for large soft_max accumulates too much error ggml-ci * ggml : alternative ALiBi without extra tensor We compute the slopes in the kernel ggml-ci * cuda : add ALiBi support in ggml_soft_max_ext ggml-ci * ggml : deprecate ggml_alibi * ggml : support multi-sequence ALiBi (Metal) ggml-ci * cuda : add multi-seq ALiBi + remote F16 soft_max ggml-ci * ggml : update deprecation message * ggml : fix pos ptr when no ALiBi ggml-ci * cuda : fix performance (pow -> powf) * cuda : precompute ALiBi constants * metal : pre-compute ALiBi slopes ggml-ci * llama : init kq_pos only if needed ggml-ci * test-backend-ops : add null pos test to soft_max test-backend-ops : replace soft_max tests ggml-ci --------- Co-authored-by: slaren <slarengh@gmail.com>
2024-02-16ggml : add numa options (#5377)bmwl
* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverted Makefile * Fixed include * Removed sched.h from ggml.h, moved ggml_get_numa_affinity into ggml.c, removed trailing whitespace and fixed up a few inconsistent variables * removed trailing whitespace * Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h * Reverting Makefile * Fixed a number of issues with the move from BOOL to ggml_numa_strategies. Added a note about mirror mode note being implemented yet * Removing MIRROR_MODE code for this PR * Removing last bit of MIRROR_MODE code for this PR * Removing unneeded branch in server.cpp example and moving get_numa_affinity and making it static * Fixed lingering init_llama_backend() bool calls in tests and examples * Remote enum llama_numa_strategies * Revert bad merge with dynatemp flags * add missing enum ggml_numa_strategies declaration and revert sync problem with master * add missing enum ggml_numa_strategies declaration * fixed ggml_init_numa variable * Update ggml.h Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * Update READMEs with info about numa flags, change INTERLEAVE strategy name to DISTRIBUTE everywhere, implement the improved distribution strategy from @rankaiyx, fix a spelling mistake and un-merge some bad merges * split numa init out from llama_backend_init and created llama_numa_init. Updated all code paths and samples * Fix up some boolean vs enum comparisons * Added #ifdefs for non-Linux OS that don't have cpu_set_t datatype * Update ggml.h Align enum values Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c Remove whitespace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update ggml.c align paremeters Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/server/server.cpp remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update common/common.cpp Remove whitespace and align brace Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * unified ggml_numa_strategy enum and fixed text alignment in server.cpp example * Update ggml.c simplified return for platforms without NUMA support Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> * removed redundant else from cli argument processing of --numa * whitespace --------- Co-authored-by: root <root@nenya.lothlorien.ca> Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-02-13tests : multi-thread the tokenizer tests (#5474)Georgi Gerganov
* tests : multi-thread the tokenizer tests ggml-ci * unicode : fix data race for unidentified codepoints ggml-ci * unicode : minor style fixes ggml-ci
2024-02-13tests : disable moe test (#5473)Georgi Gerganov
2024-02-11ggml : add mmla kernels for quantized GEMM (#4966)snadampal
* ggml: aarch64: implement smmla kernel for q8_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q8_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_1_q8_1 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_1_q8_1 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: update unit tests for the new vec_dot interface * llama.cpp: add MATMUL_INT8 capability to system_info
2024-02-08sampling: fix top_k <= 0 (#5388)Johannes Gäßler
* sampling: fix top_k <= 0 * Update llama.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-08tests : .gitignore obj filesGeorgi Gerganov
2024-02-03refactor : switch to emplace_back to avoid extra object (#5291)Michael Klimenko
2024-01-31llava : add MobileVLM support (#5132)JidongZhang-THU
* New Feature: 1. Sum_Rows: fix cuda kernel overflow fix block shape error when nrows too big 2. Im2Col: Support Batch in cuda Support f32 to f32 both in cpu && cuda 3. DepthWiseConv: Support by Im2Col && MulMat 4. Pool_2d: Supoort avg pooling in cuda 5. HardSigmoid: Imp in cuda 6. HardSwish: Imp in cuda * fix tabs instead of spaces * code clean * CUDA POOL2D * ADD POOL2D test case in test-backend-ops.cpp * code clean * fix pool2d_kernel nits * fix bug in pool2d kernel * fix avg pooling, count_include_pad nits * test-backend-ops : add more pool_2d tests * cuda : fix warnings and formatting * ggml : check types in release builds too in pool_2d * test-backend-ops : remove f16 pool_2d tests * cuda : more style fixes * Add assert in ggml_cuda_op_pool2d * pool2d float padding fallback * test-backend-ops : add dst_type to im2col --------- Co-authored-by: slaren <slarengh@gmail.com>
2024-01-30`ggml_cuda_cpy` support for 4d tensors and float16->float32 upcasting (ggml/686)John Balis
* added cuda float16->float32 upcasting to ggml_cuda_cpy * added ability to copy 4d tensors with the cuda backend * added tests for float16_>float32 upcast and 4d tensor cuda copys * added 4d copy test for float32->float16 copy * applied patch suggested by @iamlemec * simplify cpy tests --------- Co-authored-by: slaren <slarengh@gmail.com>
2024-01-30SOTA 3-bit quants (#5196)Kawrakow
* iq3_xxs: quantize/dequantize RMSE seems a bit high-ish at about half-way between q2_K and q3_K, so need to check more. * iq3_xxs: CUDA dequantize works * iq2_xxs: tuning quantization * iq3_xxs: starting to look better PPL on wiki.test.raw LLaMA-v1-7B: 6.4218 LLaMA-v2-7B: 6.3560 Mistral-7B : 6.0717 This is better than Q3_K_XS, with a 5% reduction in quantized model size. * iq3_xxs: CUDA dot product We have PP-512: 5891 t/s TG-128: 143.9 t/s * iq3_xxs: scalar and AVX2 dot products * iq3_xxs: ARM_NEON and Metal Metal performance is decent, ARM_NEON is pathetic * iq3_xxs: slightly better grid points * Faster iq3_xxs and iq2_xs dot products on CUDA * iq3_xxs: add some quant mix * iq3_xxs: fix failing quantization test Dot product still fails. Is this real? * iq3_xxs: hopefully fix ROCm * iq3_xxs: failing tests This time the dot product accuracy did find an actual bug in the AVX2 implementation. * Add IQ3_XXS to test-backend-ops --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-29Nomic Vulkan backend (#4456)Jared Van Bortel
Signed-off-by: Jared Van Bortel <jared@nomic.ai> Co-authored-by: niansa <anton-sa@web.de> Co-authored-by: Adam Treat <treat.adam@gmail.com> Co-authored-by: Aaron Miller <apage43@ninjawhale.com> Co-authored-by: ToKiNoBug <tokinobug@163.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: slaren <slarengh@gmail.com>
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-20 23:23:44 +0000