423 Commits

Author	SHA1	Message	Date
Georgi Gerganov	8125e6cbfc	server : don't overfill the batch during infill (#10018) ... ggml-ci	2024-10-28 08:49:32 +02:00
wwoodsTM	ff252ea48e	llama : add DRY sampler (#9702) ... * sampling : add DRY sampler (post-refactor) * DRY: Trying to fix coauthors, removed unneeded line * DRY: Fixed redundant code * DRY: Fixed crash issue due to DRY being in chain but uninitialized --------- Co-authored-by: l3utterfly <gc.pthzfoldr@gmail.com> Co-authored-by: pi6am <34464159+pi6am@users.noreply.github.com>	2024-10-25 19:07:34 +03:00
Michael Podvitskiy	d80fb71f8b	llama: string_split fix (#10022) ... * llama: Refactor string_split to use template specialization, fixes parsing strings with spaces * llama: Add static_assert in the string_split template to ensure the correct template specialization is used for std::string	2024-10-25 17:57:54 +02:00
Georgi Gerganov	bc5ba007b2	server : check that the prompt fits in the slot's context (#10030) ... ggml-ci	2024-10-25 10:13:46 +03:00
Xuan Son Nguyen	958367bf53	server : refactor slot input data, move tokenizer to HTTP thread (#10023) ... * server : refactor slot input data, move tokenizer to HTTP thread * move prompt_tokens.empty() check * fix incorrect if branch * fix infinite generation loop * bring back infill validation * add infill test * try fixing format_infill * fix test * remove redundant code * rename completion to inference * update docs * use llama_tokens everywhere	2024-10-24 21:51:22 +02:00
wwoodsTM	0a1c750c80	server : samplers accept the prompt correctly (#10019)	2024-10-23 22:27:51 +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
Georgi Gerganov	8901755ba3	server : add n_indent parameter for line indentation requirement (#9929) ... ggml-ci	2024-10-18 07:32:19 +03:00
Joe Eli McIlvain	66c2c93082	grammar : fix JSON Schema for string regex with top-level alt. (#9903) ... Prior to this commit, using a JSON Schema containing a string with `pattern` regular expression that uses top-level alternation (e.g. `"pattern": "^A|B|C|D$"`) would result in invalid JSON output from the constrained sampling grammar, because it ended up creating a grammar rule like this for the string: ``` thing ::= "\"" "A" | "B" | "C" | "D" "\"" space ``` Note that this rule will only match a starting quote for the "A" case, and will only match an ending quote for the "D" case, so this rule will always produce invalid JSON when used for sampling (that is, the JSON will always be lacking the starting quote, the ending quote, or both). This was fixed in a simple way by adding parentheses to the generated rule (for all string pattern rules, to keep it simple), such that the new generated rule looks like this (correct): ``` thing ::= "\"" ("A" | "B" | "C" | "D") "\"" space ```	2024-10-16 19:03:24 +03:00
Alexey Parfenov	1f66b699c4	server : fix the disappearance of the end of the text (#9867) ... * server: fix the disappearance of the end of the text when streaming with stop strings * simplify "send text" checks	2024-10-16 11:35:53 +03:00
Georgi Gerganov	223c25a72f	server : improve infill context reuse (#9894) ... ggml-ci	2024-10-15 16:28:55 +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	dcdd535302	server : update preact (#9895)	2024-10-15 12:48:44 +03:00
VoidIsVoid	a89f75e1b7	server : handle "logprobs" field with false value (#9871) ... Co-authored-by: Gimling <huangjl@ruyi.ai>	2024-10-14 10:04:36 +03:00
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	c7181bd294	server : reuse cached context chunks (#9866) ... ggml-ci	2024-10-13 18:52:48 +03:00
Georgi Gerganov	edc265661c	server : add option to time limit the generation phase (#9865) ... ggml-ci	2024-10-12 16:14:27 +03:00
Georgi Gerganov	1bde94dd02	server : remove self-extend features (#9860) ... * server : remove self-extend ggml-ci * server : fix context limit check to use slot.n_past ggml-ci	2024-10-12 16:06:31 +03:00
Georgi Gerganov	95c76e8e92	server : remove legacy system_prompt feature (#9857) ... * server : remove legacy system_prompt feature ggml-ci * readme : update [no ci] * server : fix non-transformer logic + remove response from /props	2024-10-12 14:51:54 +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	7eee341bee	common : use common_ prefix for common library functions (#9805) ... * common : use common_ prefix for common library functions --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-10-10 22:57:42 +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
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
Daniel Kleine	133c7b46b3	Fixed RNG seed docs (#9723) ... * Update README.md fixed RNG seed info * changed print format to unsigned	2024-10-04 10:54:44 +02:00
vb	08a43d05b6	py : update transfomers version (#9694) ... * update transfomers version. * update hfh version.	2024-09-30 18:03:47 +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
Xuan Son Nguyen	afbbfaa537	server : add more env vars, improve gen-docs (#9635) ... * server : add more env vars, improve gen-docs * update server docs * LLAMA_ARG_NO_CONTEXT_SHIFT	2024-09-25 14:05:13 +02:00
StrangeBytesDev	0aa15011e3	server : add newline after chat example (#9616)	2024-09-24 09:04:39 +03:00
Xuan Son Nguyen	0b3bf966f4	server : add --no-context-shift option (#9607) ... * server : add --no-context-shift option * small fix * Update examples/server/tests/features/embeddings.feature Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * tests : minor fix * revert usage of GGML_ASSERT * update server documentation --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-23 22:23:54 +02:00
Georgi Gerganov	6026da52d6	server : clean-up completed tasks from waiting list (#9531) ... ggml-ci	2024-09-19 12:44:53 +03:00
Vinesh Janarthanan	8a308354f6	server : match OAI structured output response (#9527)	2024-09-18 09:50:34 +03:00
Eric Zhang	f799155ab8	server : fix OpenSSL build (remove obsolete LOG_INFO) (#9529)	2024-09-18 09:28:20 +03:00
Bert Wagner	8b836ae731	arg : add env variable for parallel (#9513) ... * add env variable for parallel * Update README.md with env: LLAMA_ARG_N_PARALLEL	2024-09-17 16:35:38 +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
VoidIsVoid	dcdcee3a74	server: add data: [DONE] to /chat/completions stream response (#9459)	2024-09-14 11:36:44 +02:00
Xuan Son Nguyen	feff4aa846	server : add loading html page while model is loading (#9468) ... * Adding loading page for '/' server requests * set content when model is loading * removed loading html file * updated cmakelist * updated makefile * cleaned up whitespace * cleanup for PR removed error * updated server test to handle 503 HTML * updated server test to handle 503 HTML * ca†ch 503 before parsing json * revert test * account for both api and web browser requests * precommit corrections * eol fix * revert changes to pre-commit * removed print statement * made loading message more descriptive * also support .html files --------- Co-authored-by: VJHack <flymyplane21@gmail.com> Co-authored-by: Vinesh Janarthanan <36610342+VJHack@users.noreply.github.com>	2024-09-13 14:23:11 +02:00
Mathijs Henquet	78203641fe	server : Add option to return token pieces in /tokenize endpoint (#9108) ... * server : added with_pieces functionality to /tokenize endpoint * server : Add tokenize with pieces tests to server.feature * Handle case if tokenizer splits along utf8 continuation bytes * Add example of token splitting * Remove trailing ws * Fix trailing ws * Maybe fix ci * maybe this fix windows ci? --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>	2024-09-12 22:30:11 +02:00
slaren	49006c67b4	llama : move random seed generation to the samplers (#9398) ... * llama_sampler_penalties : clamp penalty_last_n to zero	2024-09-10 18:04:25 +02:00
Xuan Son Nguyen	bfe76d4a17	common : move arg parser code to arg.cpp (#9388) ... * common : move arg parser to arg.cpp * better categorize args * add cmake * missing climits * missing cstdarg * common : more explicit includes * fix build * refactor gpt_params_parse * update server readme * fix test --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-09 23:36:09 +02:00
slaren	5fb5e24811	llama : minor sampling refactor (2) (#9386)	2024-09-09 17:10:46 +02:00
Georgi Gerganov	faf69d4237	llama : sanitize invalid tokens (#9357) ... * common : do not add null tokens during warmup ggml-ci * llama : check that the input tokens are valid ggml-ci * tests : fix batch size of bert model ggml-ci	2024-09-08 00:33:13 +03:00
Xuan Son Nguyen	1b9ae5189c	common : refactor arg parser (#9308) ... * (wip) argparser v3 * migrated * add test * handle env * fix linux build * add export-docs example * fix build (2) * skip build test-arg-parser on windows * update server docs * bring back missing --alias * bring back --n-predict * clarify test-arg-parser * small correction * add comments * fix args with 2 values * refine example-specific args * no more lamba capture Co-authored-by: slaren@users.noreply.github.com * params.sparams * optimize more * export-docs --> gen-docs	2024-09-07 20:43:51 +02:00
Georgi Gerganov	df270ef745	llama : refactor sampling v2 (#9294) ... - Add `struct llama_sampler` and `struct llama_sampler_i` - Add `llama_sampler_` API - Add `llama_sampler_chain_` API for chaining multiple samplers - Remove `LLAMA_API_INTERNAL` - Add `llama_perf_` API and remove old `llama_print_timings` and `llama_reset_timings`	2024-09-07 15:16:19 +03:00
Xuan Son Nguyen	9b2c24c099	server : simplify state machine for slot (#9283) ... * server : simplify state machine for slot * add SLOT_STATE_DONE_PROMPT * pop_deferred_task * add missing notify_one * fix passkey test * metrics : add n_busy_slots_per_decode * fix test step * add test * maybe fix AddressSanitizer? * fix deque ? * missing lock * pop_deferred_task: also notify * Update examples/server/server.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-06 23:21:29 +02:00
Xuan Son Nguyen	4a1411b4f1	server : fix missing lock (#9334)	2024-09-06 14:06:04 +02:00
Xuan Son Nguyen	48baa61ecc	server : test script : add timeout for all requests (#9282)	2024-09-02 22:08:38 +02:00
Xuan Son Nguyen	6e7d133a5f	server : refactor multitask handling (#9274) ... * server : remove multitask from server_task * refactor completions handler * fix embeddings * use res_ok everywhere * small change for handle_slots_action * use unordered_set everywhere * (try) fix test * no more "mutable" lambda * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * use deque --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-09-02 17:11:51 +02:00
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
Jan Boon	9f7d4bcf5c	server : fix crash when error handler dumps invalid utf-8 json (#9195)	2024-08-30 07:15:26 +08:00
Xuan Son Nguyen	a77feb5d71	server : add some missing env variables (#9116) ... * server : add some missing env variables * add LLAMA_ARG_HOST to server dockerfile * also add LLAMA_ARG_CONT_BATCHING	2024-08-27 11:07:01 +02:00