From c3b075f069a412b736e4723e354d8d8b7c70b341 Mon Sep 17 00:00:00 2001 From: Nexesenex <124105151+Nexesenex@users.noreply.github.com> Date: Mon, 3 Aug 2026 07:01:18 +0200 Subject: [PATCH] Chores : tidy up more typos project wide (ggml directory excluded), new -ptcall alias (#2237) * common: fix coding mistakes (typos in identifiers, flags and log strings) Fix misspelled identifiers and user-facing strings across common, server and model loading: - allow_ruless -> allow_rules (misspelled identifier used in the allowlist CLI parsing and the server slot/context code) - get_formated_timings/get_formated_generation -> get_formatted_* - 'termionated' -> 'terminated' in the fit-margin assert message - 'defaulr' -> 'default' in the YAML dump - 'overriden' -> 'overridden' in tensor buffer type override logs - 'becausee' -> 'because' in the output-tensor split log - 'etected NaNs' -> 'detected NaNs' in the imatrix error message * common: fix comment typos across src, common, include and examples Fix misspelled words in code comments: - llama.h: 'typy' -> 'type', 'transfrom' -> 'transform', 'ecoder' -> 'encoder', 'indicies' -> 'indices', 'Intializes' -> 'Initializes' - common.h: 'embendings' -> 'embeddings', 'pr' -> 'or' in the fused-indexer-topk comment - chat.cpp: 'overridde' -> 'override' - ngram-map: 'occurences' -> 'occurrences', 'stastistics' -> 'statistics' - speculative.cpp: 'dont'/'inehit' -> 'don't'/'inherit' - llama-mmap.cpp: 'dont't' -> 'don't' - llama-model.h: 'hcurrently andle' -> 'currently handle' - build_gemma3/4.cpp: 'emdeddings' -> 'embeddings' - examples: 'quantizuation', 'logprobe', 'throught', 'retrun', 'swich', 'convinient', 'temporally' (-> 'temporary'), 'temproal', 'preceed' * common: remove duplicate definitions and duplicate help entries - clip-impl.h: drop the second, identical #define TN_FFN_GATE - common.cpp: remove the duplicate '-t, --threads N' help entry that was misplaced in the export-lora section (already listed in the general section) - common.cpp: merge the two 'embedding' help groups into a single group so the embedding options are listed together - llama.cpp: remove the redundant LLAMA_MAX_LAYERS define (llama-hparams.h already defines the same value and is included by llama.cpp) * common: fix remaining typos (accomodate, recommanded, occurences, occassionally) - accomodate -> accommodate in src/llama.cpp comment - recommanded -> recommended in quantize.cpp user-facing output - occurences -> occurrences in test-chat.cpp JSON string - occassionally -> occasionally in vendor/stb/stb_image_resize2.h comment Note: tokenizer.ggml.seperator_token_id kept as-is to match GGUF spec * common: remove duplicate help entries - remove the duplicate '--reasoning-budget N' help entry that was repeated in the main section (introduced in e0596bf6146 'Autoparser - complete refactoring of parser architecture (PR 1376)') - remove the second '--parallel-tool-calls' help entry that advertised the '-ptc' short flag, which belongs to '--print-token-count' (introduced in e0596bf6146 'Autoparser - complete refactoring of parser architecture (PR 1376)'); the '-ptc' alias was non-functional for '--parallel-tool-calls' because the parser only binds it to '--print-token-count' The canonical help entries are kept: - '--reasoning-budget N' is listed once - '--parallel-tool-calls' is listed once (without the conflicting '-ptc' alias) * common: remove duplicate LOG_ENABLE define - the '#undef LOG_ENABLE / #define LOG_ENABLE() // dummy stub' pair was repeated verbatim inside the LOG_DISABLE_LOGS section - remove the second occurrence (introduced in a2588b53e11 'main : log file (PR 2748)') * llama-bench: align MLA and attention-max-batch flags with common tools llama-bench used '--mla-attn' and '--attn-max-batch' while the common CLI parsing (common/common.cpp) uses '--mla-use' and '--attention-max-batch' for the same features. This made the flags inconsistent across tools. - update the help text to advertise the canonical names '--mla-use' and '--attention-max-batch' - keep the old '--mla-attn' and '--attn-max-batch' spellings working as aliases so existing scripts are not broken The divergent names were introduced in 3e536b95b08 'Add optional MLA (PR 188)'. * fix typos in comments and user-facing strings - ngram-map.cpp: 'Do we haven a existing' -> 'Do we have an existing' (introduced in 1cb7e1bf39d 'spec : add self speculative decoding, ngram and refactor (PR 1261)') - build_mamba.cpp: 'weigth' -> 'weight' (introduced in 8befd92ea5f 'Refactor model compute graphs (PR 1651)') - gguf-split.cpp: 'one of splits have 0 tensors' -> 'one of the splits has 0 tensors' (introduced in 75b580db0a3 'split: allow --split-max-size option (PR 6343)') - gguf-split.cpp: 'merged from %d split' -> 'merged from %d splits' (introduced in 1b5523dc796 'gguf-split: split and merge gguf per batch of tensors (PR 6135)') - convert-llama2c-to-ggml.cpp: missing opening quote in the help line, '(default %s\\')' -> '(default '%s\\')' (introduced in bb9ebb43943 'Adding support for llama2.c models (PR 2559)') * harmonize British and American spelling to American English The codebase uses American English (e.g. --embd-normalize, --color), but a few strings/comments still used British spellings. Unify them: - 'normalisation' -> 'normalization' in common.h, common.cpp help text and code comment, and llama-build-context.cpp comment - 'colorise' -> 'colorize' in the --color help text (common.cpp) - 'behaviour' -> 'behavior' in a chat.cpp warning and a llama.cpp comment - also fix 'openai' -> 'OpenAI' capitalization in the embedding help text and common.h comment (embedding output format is OpenAI-style) * common: fix help text formatting inconsistencies - '-smf16'/'--split-mode-f16' and '-smf32'/'--split-mode-f32' help entries displayed hardcoded 'true'/'false' as the default value; show the actual state derived from params.reduce_type instead - '-no-mmad' help entry had 'fused_mmad?' without a space before the ternary operator - '--reasoning-tokens' help continuation lines used tab characters for indentation while the sibling '--reasoning-format' entry uses spaces; convert to consistent space indentation * common: revert smf16/smf32 help text default display change Revert the '-smf16'/'--split-mode-f16' and '-smf32'/'--split-mode-f32' help entries back to their original hardcoded 'true'/'false' default display. The change to derive the default from params.reduce_type was not desired; the split-mode options are legacy and the hardcoded defaults reflect their intended meaning. The other formatting fixes in the same area (fused_mmad ternary spacing and the reasoning-tokens tab-to-space indentation) are kept. * llama-bench: fix help text column alignment The --mla-use and --attention-max-batch help lines introduced by the flag alignment landed one column off from the sibling entries ((default: at column 51 instead of 50). Adjust the padding so all help lines align. * common: fix help text defaults for graph-reduce-type and log-format Mismatch 1: -grt, --graph-reduce-type help shows default "f32", but actual default (common.h:463) is "f16" and llama.cpp uses GGML_TYPE_F16. Mismatch 2: --log-format help shows default "json", but actual default (common.h:536 log_json=false) is text. * common: add -ptcall short flag for --parallel-tool-calls * typo --- common/chat.cpp | 4 +- common/common.cpp | 47 +++++++++---------- common/common.h | 10 ++-- common/log.h | 3 -- common/ngram-map.cpp | 4 +- common/ngram-map.h | 6 +-- common/speculative.cpp | 2 +- examples/benchmark/benchmark-matmult.cpp | 2 +- .../convert-llama2c-to-ggml.cpp | 2 +- .../cvector-generator/cvector-generator.cpp | 2 +- examples/cvector-generator/pca.hpp | 4 +- examples/gguf-hash/gguf-hash.cpp | 2 +- examples/gguf-split/gguf-split.cpp | 4 +- examples/imatrix/imatrix.cpp | 2 +- examples/llama-bench/llama-bench.cpp | 8 ++-- examples/mtmd/clip-impl.h | 1 - examples/mtmd/clip.cpp | 2 +- examples/mtmd/mtmd.cpp | 2 +- examples/perplexity/perplexity.cpp | 2 +- examples/quantize-stats/quantize-stats.cpp | 2 +- examples/quantize/quantize.cpp | 2 +- examples/server/function_calls.hpp | 2 +- examples/server/server-context.cpp | 28 +++++------ examples/server/server-context.h | 8 ++-- include/llama.h | 16 +++---- src/graphs/build_gemma3.cpp | 2 +- src/graphs/build_gemma4.cpp | 2 +- src/graphs/build_mamba.cpp | 2 +- src/llama-build-context.cpp | 2 +- src/llama-load-tensors.cpp | 6 +-- src/llama-mmap.cpp | 2 +- src/llama-model.h | 2 +- src/llama.cpp | 7 +-- tests/test-chat.cpp | 2 +- vendor/stb/stb_image_resize2.h | 2 +- 35 files changed, 92 insertions(+), 104 deletions(-) diff --git a/common/chat.cpp b/common/chat.cpp index 60ea5c403..ae7bc77b8 100644 --- a/common/chat.cpp +++ b/common/chat.cpp @@ -243,7 +243,7 @@ using chat_template_caps = jinja::caps; struct common_chat_templates { bool add_bos; bool add_eos; - bool has_explicit_template; // Model had builtin template or template overridde was specified. + bool has_explicit_template; // Model had builtin template or template override was specified. std::unique_ptr template_default; // always set (defaults to chatml) std::unique_ptr template_tool_use; }; @@ -2672,7 +2672,7 @@ static common_chat_params common_chat_templates_apply_jinja(const struct common_ } if (caps.supports_tool_calls && !caps.supports_tools) { LOG_WRN( - "Template supports tool calls but does not natively describe tools. The fallback behaviour used may " + "Template supports tool calls but does not natively describe tools. The fallback behavior used may " "produce bad results, inspect prompt w/ --verbose & consider overriding the template.\n"); } } diff --git a/common/common.cpp b/common/common.cpp index 677308a33..b67d80aa9 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1809,7 +1809,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa return true; } if (arg == "-ictk" || arg == "--indexer-cache-type-k") { - LLAMA_LOG_WARN("================== Quantized inexer cache has been disabled for now => argument '%s' ignored\n", arg.c_str()); + LLAMA_LOG_WARN("================== Quantized indexer cache has been disabled for now => argument '%s' ignored\n", arg.c_str()); ++i; //params.indexer_cache_type_k = argv[++i]; return true; @@ -2312,10 +2312,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa } if (arg == "--allowlist-unicode-rule") { CHECK_ARG - if (params.allow_ruless.size() == 0) { - params.allow_ruless.push_back({}); + if (params.allow_rules.size() == 0) { + params.allow_rules.push_back({}); } - params.allow_ruless.back().push_back(argparse_allowlist_unicode_rule(argv[i])); + params.allow_rules.back().push_back(argparse_allowlist_unicode_rule(argv[i])); return true; } if (arg == "--allowlist-pieces") { @@ -2326,7 +2326,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa if (arg == "--allowlist-keyword") { CHECK_ARG params.allow_kws.push_back(argv[i]); - params.allow_ruless.push_back({}); + params.allow_rules.push_back({}); return true; } if (arg == "--allowlist-keyword-delay") { @@ -2733,7 +2733,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa params.prefill_assistant = false; return true; } - if (arg == "--parallel-tool-calls") { + if (arg == "-ptcall" || arg == "--parallel-tool-calls") { params.parallel_tool_calls = true; return true; } @@ -3019,7 +3019,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "*", " --verbose-prompt", "print a verbose prompt before generation (default: %s)", params.verbose_prompt ? "true" : "false" }); options.push_back({ "*", "-dr, --dry-run", "skip loading tensors in the files"}); options.push_back({ "*", " --no-display-prompt", "don't print prompt at generation (default: %s)", !params.display_prompt ? "true" : "false" }); - options.push_back({ "*", "-co, --color", "colorise output to distinguish prompt and user input from generations (default: %s)", params.use_color ? "true" : "false" }); + options.push_back({ "*", "-co, --color", "colorize output to distinguish prompt and user input from generations (default: %s)", params.use_color ? "true" : "false" }); options.push_back({ "*", "-s, --seed SEED", "RNG seed (default: %d, use random seed for < 0)", params.seed }); options.push_back({ "*", "-t, --threads N", "number of threads to use during generation (default: %d)", params.n_threads }); options.push_back({ "*", "-tb, --threads-batch N", "number of threads to use during batch and prompt processing (default: same as --threads)" }); @@ -3059,7 +3059,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "*", "-no-fmoe, --no-fused-moe", "disable fused MoE (default: %s)", params.fused_moe_up_gate ? "enabled" : "disabled" }); options.push_back({ "*", "-ger, --grouped-expert-routing", "enable grouped expert routing (default: %s)", params.grouped_expert_routing ? "enabled" : "disabled" }); options.push_back({ "*", "-no-fug, --no-fused-up-gate", "disable fused up-gate (default: %s)", params.fused_up_gate ? "enabled" : "disabled" }); - options.push_back({ "*", "-no-mmad, --no-fused-mul-multiadd", "disable fused mul-multi_add (default: %s)", params.fused_mmad? "enabled" : "disabled" }); + options.push_back({ "*", "-no-mmad, --no-fused-mul-multiadd", "disable fused mul-multi_add (default: %s)", params.fused_mmad ? "enabled" : "disabled" }); //options.push_back({ "*", "-rcache, --rope-cache", "enable RoPE cache (default: %s)", params.rope_cache ? "enabled" : "disabled" }); options.push_back({ "*", "-gr, --graph-reuse", "enable graph reuse (default: %s)", params.graph_reuse ? "enabled" : "disabled" }); options.push_back({ "*", "-no-gr, --no-graph-reuse", "disable graph reuse (default: %s)", !params.graph_reuse ? "enabled" : "disabled" }); @@ -3070,7 +3070,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "*", "-vhad, --v-cache-hadamard", "Use Hadamard transform for V-cache (default: %d)", params.v_cache_hadamard}); options.push_back({ "*", "-smf16, --split-mode-f16", "Use f16 for data exchange between GPUs (default: %d)", true}); options.push_back({ "*", "-smf32, --split-mode-f32", "Use f32 for data exchange between GPUs (default: %d)", false}); - options.push_back({ "*", "-grt, --graph-reduce-type", "Type for data exchange between GPUs (default: %s)", "f32"}); + options.push_back({ "*", "-grt, --graph-reduce-type", "Type for data exchange between GPUs (default: %s)", "f16"}); options.push_back({ "*", "-gap, --graph-attn-precision", "Flash-attn precision under -sm graph (default: %s)", "f16"}); options.push_back({ "*", "-smgs, --split-mode-graph-scheduling", "Force Split Mode Graph Scheduling (default: %d)", params.split_mode_graph_scheduling}); options.push_back({ "*", "-sas, --scheduler-async", "Async evaluation of compute graphs (default: %d)", params.scheduler_async}); @@ -3166,7 +3166,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param "if suffix/prefix are specified, template will be disabled\n" "only commonly used templates are accepted:\n" "https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template" }); - options.push_back({ "main", " --parallel-tool-calls", "enable parallel tool calls\n" }); + options.push_back({ "main", "-ptcall, --parallel-tool-calls", "enable parallel tool calls\n" }); options.push_back({ "main", " --chat-template JINJA_TEMPLATE", "use jinja template for chat (default: disabled)\n" }); options.push_back({ "main", " --chat-template-file file_with_JINJA_TEMPLATE", @@ -3183,17 +3183,15 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "main", " --reasoning-budget N", "token budget for thinking: -1 for unrestricted, 0 for immediate end, N>0 for token budget (default: -1)" }); options.push_back({ "main", " --reasoning-tokens FORMAT", "exclude reasoning tokens to select the slot more accurately.\n" - "none: include all tokens\n" - "auto: exclude all tokens between and \n" - "Or comma separated start and end tokens such as [THINK],[/THINK]\n" - "(default: auto)" }); + "none: include all tokens\n" + "auto: exclude all tokens between and \n" + "Or comma separated start and end tokens such as [THINK],[/THINK]\n" + "(default: auto)" }); options.push_back({ "main", " --reasoning-budget-message", "message injected before the end-of-thinking tag when reasoning budget is exhausted (default: none)" }); options.push_back({ "main", " --skip-chat-parsing", "force a pure content parser, even if a Jinja template is specified; model will output everything " "in the content section, including any reasoning and/or tool calls (default: disabled)" }); - options.push_back({ "main", " --reasoning-budget N", "token budget for thinking: -1 for unrestricted, 0 for immediate end, N>0 for token budget (default: -1)" }); options.push_back({ "main", " --no-prefill-assistant", "whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)\n" "when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled\n" }); - options.push_back({ "main", " -ptc, --parallel-tool-calls", "enable parallel tool calls\n" }); options.push_back({ "grammar" }); options.push_back({ "*", " --grammar GRAMMAR", "BNF-like grammar to constrain generations (see samples in grammars/ dir) (default: '%s')", sparams.grammar.grammar.c_str() }); options.push_back({ "*", " --grammar-file FNAME", "file to read grammar from" }); @@ -3206,6 +3204,9 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param "pooling type for embeddings, use model default if unspecified" }); options.push_back({ "embedding", " --attention {causal,non-causal}", "attention type for embeddings, use model default if unspecified" }); + options.push_back({ "embedding", " --embd-normalize", "normalization for embeddings (default: %d) (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)", params.embd_normalize }); + options.push_back({ "embedding", " --embd-output-format", "empty = default, \"array\" = [[],[]...], \"json\" = OpenAI style, \"json+\" = same \"json\" + cosine similarity matrix" }); + options.push_back({ "embedding", " --embd-separator", "separator of embeddings (default \\n) for example \"<#sep#>\"" }); options.push_back({ "context hacking" }); options.push_back({ "*", " --rope-scaling {none,linear,yarn}", @@ -3391,11 +3392,6 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "bench", "-wb, --warmup-batch", "run a warmup batch before measurement" }); options.push_back({ "bench", " --output-format FORMAT", "output format: table, jsonl, or csv (default: table)" }); - options.push_back({ "embedding" }); - options.push_back({ "embedding", " --embd-normalize", "normalisation for embeddings (default: %d) (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)", params.embd_normalize }); - options.push_back({ "embedding", " --embd-output-format", "empty = default, \"array\" = [[],[]...], \"json\" = openai style, \"json+\" = same \"json\" + cosine similarity matrix" }); - options.push_back({ "embedding", " --embd-separator", "separator of embeddings (default \\n) for example \"<#sep#>\"" }); - options.push_back({ "server" }); options.push_back({ "server", " --host HOST", "ip address to listen (default: %s)", params.hostname.c_str() }); options.push_back({ "server", " --port PORT", "port to listen (default: %d)", params.port }); @@ -3417,7 +3413,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "server", "-spf, --system-prompt-file FNAME", "set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications" }); options.push_back({ "server", " --log-format {text,json}", - "log output format: json or text (default: json)" }); + "log output format: json or text (default: text)" }); options.push_back({ "server", " --metrics", "enable prometheus compatible metrics endpoint (default: %s)", params.endpoint_metrics ? "enabled" : "disabled" }); options.push_back({ "server", " --no-slots", "disables slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled" }); options.push_back({ "server", " --slot-save-path PATH", "path to save slot kv cache (default: disabled)" }); @@ -3457,7 +3453,6 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param options.push_back({ "export-lora", "-m, --model", "model path from which to load base model (default '%s')", params.model.c_str() }); options.push_back({ "export-lora", " --lora FNAME", "path to LoRA adapter (can be repeated to use multiple adapters)" }); options.push_back({ "export-lora", " --lora-scaled FNAME S", "path to LoRA adapter with user defined scaling S (can be repeated to use multiple adapters)" }); - options.push_back({ "*", "-t, --threads N", "number of threads to use during computation (default: %d)", params.n_threads }); options.push_back({ "export-lora", "-o, --output FNAME", "output file (default: '%s')", params.lora_outfile.c_str() }); printf("usage: %s [options]\n", argv[0]); @@ -4268,7 +4263,7 @@ struct llama_model_params common_model_params_to_llama(const gpt_params & params } if (!params.fit_margin_array.empty()) { GGML_ASSERT(params.fit_margin_array.size() % 2 == 0 && "Fit margin array does not have even number of elements"); - GGML_ASSERT(params.fit_margin_array[params.fit_margin_array.size()-2] == -1 && "Fit margin array is not correctly termionated"); + GGML_ASSERT(params.fit_margin_array[params.fit_margin_array.size()-2] == -1 && "Fit margin array is not correctly terminated"); mparams.fit_margin_array = params.fit_margin_array.data(); } @@ -4973,7 +4968,7 @@ void common_embd_normalize(const float * inp, float * out, int n, int embd_norm) double sum = 0.0; switch (embd_norm) { - case -1: // no normalisation + case -1: // no normalization sum = 1.0; break; case 0: // max absolute @@ -5384,7 +5379,7 @@ void yaml_dump_non_result_info(FILE * stream, const gpt_params & params, const l //fprintf(stream, "split_mode_f16: %s # default: true\n", params.split_mode_f16 ? "true" : "false"); fprintf(stream, "reduce_type: %s # default f16\n", params.reduce_type.c_str()); fprintf(stream, "scheduler_async: %s # default: false\n", params.scheduler_async ? "true" : "false"); - fprintf(stream, "ser: %d,%g # defaulr: -1,0\n", params.min_experts, params.thresh_experts); + fprintf(stream, "ser: %d,%g # default: -1,0\n", params.min_experts, params.thresh_experts); fprintf(stream, "temp: %f # default: 0.8\n", sparams.temp); const std::vector tensor_split_vector(params.tensor_split, params.tensor_split + llama_max_devices()); diff --git a/common/common.h b/common/common.h index 84ab03ee4..ada90425e 100644 --- a/common/common.h +++ b/common/common.h @@ -364,7 +364,7 @@ struct gpt_params { ,uint32_t // upper codepoint ,std::string // unicode script name ,float // bias - >>> allow_ruless; + >>> allow_rules; std::vector allow_pieces; // each token to allowlist std::vector allow_kws; // keywords size_t allow_kw_delay; // minimum n_decoded before first keyword is active @@ -421,7 +421,7 @@ struct gpt_params { bool rope_cache = false; // if to use RoPE cache (for supported models) bool graph_reuse = true; // if to reuse compute graphs bool dsa = false; // enable GLM DSA sparse attention (off by default; opt-in via --dsa) - bool fused_idx_topk = true; // enable the fused indexer topk op (off by default; opt-in via -fidx pr --fused-indexer-topk) + bool fused_idx_topk = true; // enable the fused indexer topk op (off by default; opt-in via -fidx or --fused-indexer-topk) int dsa_top_k = -1; // DSA top-k override (<0 => use the model's configured indexer_top_k) int min_experts = -1; float thresh_experts = 0; @@ -486,9 +486,9 @@ struct gpt_params { // embedding bool embedding = false; // get only sentence embedding - int32_t embd_normalize = 2; // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm) - std::string embd_out = ""; // empty = default, "array" = [[],[]...], "json" = openai style, "json+" = same "json" + cosine similarity matrix - std::string embd_sep = "\n"; // separator of embendings + int32_t embd_normalize = 2; // normalization for embeddings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm) + std::string embd_out = ""; // empty = default, "array" = [[],[]...], "json" = OpenAI style, "json+" = same "json" + cosine similarity matrix + std::string embd_sep = "\n"; // separator of embeddings // server params int32_t port = 8080; // server listens on this network port diff --git a/common/log.h b/common/log.h index 551c3e8b6..783ccf92a 100644 --- a/common/log.h +++ b/common/log.h @@ -830,9 +830,6 @@ inline std::string LOG_BATCH_TOSTR_PRETTY(const C & ctx, const B & batch) #undef LOG_ENABLE #define LOG_ENABLE() // dummy stub -#undef LOG_ENABLE -#define LOG_ENABLE() // dummy stub - #undef LOG_SET_TARGET #define LOG_SET_TARGET(...) // dummy stub diff --git a/common/ngram-map.cpp b/common/ngram-map.cpp index affb26c1a..94f6726a4 100644 --- a/common/ngram-map.cpp +++ b/common/ngram-map.cpp @@ -416,7 +416,7 @@ void common_ngram_map_draft(common_ngram_map & map, continue; } - // Do we haven a existing value m-gram or a new one after the key at index i? + // Do we have an existing value m-gram or a new one after the key at index i? size_t idx_begin_value_key = i + n; int idx_value = -1; for (int v = 0; v < COMMON_NGRAM_MAX_VALUES; ++v) { @@ -461,7 +461,7 @@ void common_ngram_map_draft(common_ngram_map & map, slot_max = v; } } - // What is sum of the other occurences? + // What is sum of the other occurrences? uint32_t sum_occur = 0; for (int v = 0; v < COMMON_NGRAM_MAX_VALUES; ++v) { if (v == slot_max) { diff --git a/common/ngram-map.h b/common/ngram-map.h index 41b953044..97608ef17 100644 --- a/common/ngram-map.h +++ b/common/ngram-map.h @@ -44,16 +44,16 @@ llama_tokens common_ngram_simple_draft( // statistics of a m-gram after a known n-gram struct common_ngram_map_value { size_t value_idx = 0; // index of value m-gram in token-history (0 if unused) - uint16_t value_num = 0; // number of occurences of this value m-gram after the key n-gram (0 in an unused values-slot) + uint16_t value_num = 0; // number of occurrences of this value m-gram after the key n-gram (0 in an unused values-slot) int16_t n_accepted = -1; // number of accepted tokens at last draft (-1 if unused) }; // statistics of a n-gram struct common_ngram_map_key { size_t key_idx; // index of key n-gram in token-history - size_t stat_idx; // index of last token of stastistics computation (key_num, values) + size_t stat_idx; // index of last token of statistics computation (key_num, values) - uint16_t key_num; // number of occurences of this key n-gram in token-history + uint16_t key_num; // number of occurrences of this key n-gram in token-history common_ngram_map_value values[COMMON_NGRAM_MAX_VALUES]; // some known values after the key }; diff --git a/common/speculative.cpp b/common/speculative.cpp index 8de714dc0..9ccec66be 100644 --- a/common/speculative.cpp +++ b/common/speculative.cpp @@ -1923,7 +1923,7 @@ bool common_speculative_load_draft_model( free_command_line(argc, argv); } - // We likely dont want to inehit offload policy for MTP + // We likely don't want to inherit offload policy for MTP if (params.has_stage_type(COMMON_SPECULATIVE_TYPE_MTP)) { params_dft.ncmoe = 0; params_dft.tensor_buft_overrides.clear(); diff --git a/examples/benchmark/benchmark-matmult.cpp b/examples/benchmark/benchmark-matmult.cpp index b56a64b16..bda9cfb5f 100644 --- a/examples/benchmark/benchmark-matmult.cpp +++ b/examples/benchmark/benchmark-matmult.cpp @@ -251,7 +251,7 @@ int main(int argc, char ** argv) { #endif // Check that the matrix multiplication result is in the right ballpark - // We cannot use the exact value from the F32 multiplication because the quantizuation will be slightly different + // We cannot use the exact value from the F32 multiplication because the quantization will be slightly different float sum_of_Q4_result = tensor_sum_elements(gf31->nodes[0]); float delta = std::abs(sum_of_Q4_result - sum_of_F32_reference); float allowed_delta = (sum_of_F32_reference) / 1000 / 1000; // Let's accept an epsilon of 10^-6 diff --git a/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp b/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp index 73505f590..dc0233600 100644 --- a/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp +++ b/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp @@ -803,7 +803,7 @@ static void print_usage(int /*argc*/, char ** argv, const struct train_params * fprintf(stderr, " -h, --help show this help message and exit\n"); fprintf(stderr, " --copy-vocab-from-model FNAME path of gguf llama model or llama2.c vocabulary from which to copy vocab (default '%s')\n", params->fn_vocab_model); fprintf(stderr, " --llama2c-model FNAME [REQUIRED] model path from which to load Karpathy's llama2.c model\n"); - fprintf(stderr, " --llama2c-output-model FNAME model path to save the converted llama2.c model (default %s')\n", params->fn_llama2c_output_model); + fprintf(stderr, " --llama2c-output-model FNAME model path to save the converted llama2.c model (default '%s')\n", params->fn_llama2c_output_model); fprintf(stderr, "\n"); } diff --git a/examples/cvector-generator/cvector-generator.cpp b/examples/cvector-generator/cvector-generator.cpp index f1b92c597..c0c7c2dbb 100644 --- a/examples/cvector-generator/cvector-generator.cpp +++ b/examples/cvector-generator/cvector-generator.cpp @@ -106,7 +106,7 @@ struct callback_data { auto diff_filtered = filter_nonzero_rows(v_pos[il]); v_diff_filtered.push_back(diff_filtered); } - return v_diff_filtered; // for convinient, we return the result std::vector + return v_diff_filtered; // for convenient, we return the result std::vector } // delete zero rows from a given 2D tensor diff --git a/examples/cvector-generator/pca.hpp b/examples/cvector-generator/pca.hpp index ac7c45a7c..3d944f2b1 100644 --- a/examples/cvector-generator/pca.hpp +++ b/examples/cvector-generator/pca.hpp @@ -148,7 +148,7 @@ static struct ggml_cgraph * build_graph_piter( /*.mem_buffer =*/ buf.data(), /*.no_alloc =*/ true, // the tensors will be allocated later by ggml_allocr_alloc_graph() }; - // create a temporally context to build the graph + // create a temporary context to build the graph struct ggml_context * ctx0 = ggml_init(params0); struct ggml_cgraph * gf = ggml_new_graph(ctx0); @@ -189,7 +189,7 @@ static struct ggml_cgraph * build_graph_piter( ggml_build_forward_expand(gf, distance); } - // delete the temporally context used to build the graph + // delete the temporary context used to build the graph ggml_free(ctx0); return gf; } diff --git a/examples/gguf-hash/gguf-hash.cpp b/examples/gguf-hash/gguf-hash.cpp index e96c75117..87efd3f6a 100644 --- a/examples/gguf-hash/gguf-hash.cpp +++ b/examples/gguf-hash/gguf-hash.cpp @@ -678,7 +678,7 @@ int main(int argc, const char ** argv) { params.manifest_is_usable = true; } - // By default if no swich argument provided, assume xxh64 + // By default if no switch argument provided, assume xxh64 if (!params.xxh64 && !params.sha1 && !params.uuid && !params.sha256) { params.xxh64 = true; } diff --git a/examples/gguf-split/gguf-split.cpp b/examples/gguf-split/gguf-split.cpp index 0ab8d833a..1f957c374 100644 --- a/examples/gguf-split/gguf-split.cpp +++ b/examples/gguf-split/gguf-split.cpp @@ -233,7 +233,7 @@ struct split_strategy { i_split++; if (ctx_out != NULL) { if (gguf_get_n_tensors(ctx_out) == 0 && !allow_no_tensors) { - fprintf(stderr, "error: one of splits have 0 tensors. Maybe size or tensors limit is too small\n"); + fprintf(stderr, "error: one of the splits has 0 tensors. Maybe size or tensors limit is too small\n"); exit(EXIT_FAILURE); } ctx_outs.push_back(ctx_out); @@ -585,7 +585,7 @@ static void gguf_merge(const split_params & split_params) { gguf_free(ctx_out); } - fprintf(stderr, "%s: %s merged from %d split with %d tensors.\n", + fprintf(stderr, "%s: %s merged from %d splits with %d tensors.\n", __func__, split_params.output.c_str(), n_split, total_tensors); } diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp index 868488af3..9f269e91a 100644 --- a/examples/imatrix/imatrix.cpp +++ b/examples/imatrix/imatrix.cpp @@ -498,7 +498,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void * const float * x = (const float *)((const char *)data + i11*src1->nb[1] + i12*src1->nb[2]); if (add_and_check_nans(src1->ne[0], x, e.values.data() + e_start, e.counts.data() + e_start)) { - fprintf(stderr, "etected NaNs in %s\n", wname.c_str()); + fprintf(stderr, "detected NaNs in %s\n", wname.c_str()); exit(1); } //for (int j = 0; j < (int)src1->ne[0]; ++j) { diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 5c6fb3e55..0dadf218e 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -352,8 +352,8 @@ static void print_usage(int /* argc */, char ** argv) { printf(" -mg, --main-gpu (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str()); printf(" -nkvo, --no-kv-offload <0|1> (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str()); printf(" -fa, --flash-attn <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str()); - printf(" -mla, --mla-attn <0|1|2> (default: %s)\n", join(cmd_params_defaults.mla_attn, ",").c_str()); - printf(" -amb, --attn-max-batch (default: %s)\n", join(cmd_params_defaults.attn_max_batch, ",").c_str()); + printf(" -mla, --mla-use <0|1|2> (default: %s)\n", join(cmd_params_defaults.mla_attn, ",").c_str()); + printf(" -amb, --attention-max-batch (default: %s)\n", join(cmd_params_defaults.attn_max_batch, ",").c_str()); printf(" -ser, --smart-expert-reduction (default: %s)\n", join(cmd_params_defaults.attn_max_batch, ",").c_str()); printf(" -gr, --graph-reuse <0|1> (default: %s)\n", join(cmd_params_defaults.reuse, ",").c_str()); printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str()); @@ -702,14 +702,14 @@ static cmd_params parse_cmd_params(int argc, char ** argv) { } auto p = string_split(argv[i], split_delim); params.flash_attn.insert(params.flash_attn.end(), p.begin(), p.end()); - } else if (arg == "-mla" || arg == "--mla-attn") { + } else if (arg == "-mla" || arg == "--mla-use" || arg == "--mla-attn") { if (++i >= argc) { invalid_param = true; break; } auto p = string_split(argv[i], split_delim); params.mla_attn.insert(params.mla_attn.end(), p.begin(), p.end()); - } else if (arg == "-amb" || arg == "--attn-max-batch") { + } else if (arg == "-amb" || arg == "--attention-max-batch" || arg == "--attn-max-batch") { if (++i >= argc) { invalid_param = true; break; diff --git a/examples/mtmd/clip-impl.h b/examples/mtmd/clip-impl.h index b149d533f..d02c0bc20 100644 --- a/examples/mtmd/clip-impl.h +++ b/examples/mtmd/clip-impl.h @@ -74,7 +74,6 @@ #define TN_ATTN_K_NORM "%s.blk.%d.attn_k_norm.%s" #define TN_ATTN_Q_NORM "%s.blk.%d.attn_q_norm.%s" #define TN_FFN_DOWN "%s.blk.%d.ffn_down.%s" -#define TN_FFN_GATE "%s.blk.%d.ffn_gate.%s" #define TN_FFN_UP "%s.blk.%d.ffn_up.%s" #define TN_FFN_GATE "%s.blk.%d.ffn_gate.%s" #define TN_LN_1 "%s.blk.%d.ln1.%s" // layer norm diff --git a/examples/mtmd/clip.cpp b/examples/mtmd/clip.cpp index a17a0a2d4..3a86f1fce 100644 --- a/examples/mtmd/clip.cpp +++ b/examples/mtmd/clip.cpp @@ -307,7 +307,7 @@ struct clip_model { // embeddings ggml_tensor * class_embedding = nullptr; ggml_tensor * patch_embeddings_0 = nullptr; - ggml_tensor * patch_embeddings_1 = nullptr; // second Conv2D kernel when we decouple Conv3D along temproal dimension (Qwen2VL) + ggml_tensor * patch_embeddings_1 = nullptr; // second Conv2D kernel when we decouple Conv3D along temporal dimension (Qwen2VL) ggml_tensor * patch_bias = nullptr; ggml_tensor * position_embeddings = nullptr; diff --git a/examples/mtmd/mtmd.cpp b/examples/mtmd/mtmd.cpp index bb95c39ec..07b3693cc 100644 --- a/examples/mtmd/mtmd.cpp +++ b/examples/mtmd/mtmd.cpp @@ -578,7 +578,7 @@ struct mtmd_tokenizer { if (!ctx->tok_sli_img_start.empty()) { add_text(ctx->tok_sli_img_start); } else if (!ctx->sli_img_start_tmpl.empty()) { - // If using a template to preceed a slice image + // If using a template to precede a slice image const size_t sz = std::snprintf(nullptr, 0, ctx->sli_img_start_tmpl.c_str(), y+1, x+1) + 1; std::unique_ptr buf(new char[sz]); std::snprintf(buf.get(), sz, ctx->sli_img_start_tmpl.c_str(), y+1, x+1); diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp index 96edf516c..6bc47a12e 100644 --- a/examples/perplexity/perplexity.cpp +++ b/examples/perplexity/perplexity.cpp @@ -1103,7 +1103,7 @@ static void hellaswag_score(llama_context * ctx, const gpt_params & params) { //printf("max logprob ending idx %lu, gold ending idx %lu\n", ending_logprob_max_idx, hs_cur.gold_ending_idx); - // If the gold ending got the maximum logprobe add one accuracy point + // If the gold ending got the maximum logprob add one accuracy point if (ending_logprob_max_idx == hs_cur.gold_ending_idx) { acc += 1.0; } diff --git a/examples/quantize-stats/quantize-stats.cpp b/examples/quantize-stats/quantize-stats.cpp index d801bc15d..bcba2f85a 100644 --- a/examples/quantize-stats/quantize-stats.cpp +++ b/examples/quantize-stats/quantize-stats.cpp @@ -1685,7 +1685,7 @@ int main(int argc, char ** argv) { return 0; } - // loop throught quantization types + // loop through quantization types for (int i = 0; i < GGML_TYPE_COUNT; i++) { const ggml_type type = (ggml_type) i; if (!params.include_types.empty() && std::find(params.include_types.begin(), params.include_types.end(), i) == params.include_types.end()) { diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index e5e623148..dc5c7653a 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -187,7 +187,7 @@ static void usage(const char * executable) { printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n\n"); printf("Note: --include-weights and --exclude-weights cannot be used together\n"); printf("Note: The token embeddings tensor is loaded in system RAM, even in case of full GPU/VRAM offload.\n"); - printf("Note: The recommanded type for the output tensor is q6_K for the ffn types > iq3_xxs and < q8_0.\n\n"); + printf("Note: The recommended type for the output tensor is q6_K for the ffn types > iq3_xxs and < q8_0.\n\n"); printf("Note for the Custom Quant Scheme FTYPE:\n"); printf(" Write the specific tensor legacy quants as qN_N, the K-Quants as qN_K, the IQ-Quants as iqN_xx.\n"); printf(" Usually, attn-q-type can be one type below the chosen ffn type, and attn-v-type should be one type above.\n"); diff --git a/examples/server/function_calls.hpp b/examples/server/function_calls.hpp index 3c5c2da15..80051bd71 100644 --- a/examples/server/function_calls.hpp +++ b/examples/server/function_calls.hpp @@ -54,7 +54,7 @@ static std::string extract_content_from_mixed_input(const std::string& content, } } - // Is this the right thing to do? If we have an open thinking tag, we just retrun and do not try to + // Is this the right thing to do? If we have an open thinking tag, we just return and do not try to // remove function calls. if (is_thinking) { return result; diff --git a/examples/server/server-context.cpp b/examples/server/server-context.cpp index b4bc3a285..a9a595e15 100644 --- a/examples/server/server-context.cpp +++ b/examples/server/server-context.cpp @@ -367,7 +367,7 @@ void server_context::init() { slots.push_back(std::move(slot)); } - default_generation_settings_for_props = get_formated_generation(slots.front()); + default_generation_settings_for_props = get_formatted_generation(slots.front()); default_generation_settings_for_props["seed"] = -1; // the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens @@ -511,7 +511,7 @@ void server_slot::reset() { ban_regex.clear(); ban_regex_ci.clear(); - allow_ruless.clear(); + allow_rules.clear(); allow_pieces.clear(); allow_kws.clear(); allow_kw_delay = 0; @@ -625,7 +625,7 @@ void server_slot::release() { } -json server_slot::get_formated_timings() const { +json server_slot::get_formatted_timings() const { json timings = json{ {"prompt_n", n_prompt_tokens_processed}, {"prompt_ms", t_prompt_processing}, @@ -1686,8 +1686,8 @@ bool server_context::launch_slot_with_task(server_slot& slot, server_task& task) do // populate allowlist biases { // TODO: JSON parsing for rules and keywords - slot.allow_ruless = params_base.allow_ruless; - if (slot.allow_ruless.size() == 0) { + slot.allow_rules = params_base.allow_rules; + if (slot.allow_rules.size() == 0) { slot.allow_biasess.clear(); break; } @@ -1716,11 +1716,11 @@ bool server_context::launch_slot_with_task(server_slot& slot, server_task& task) } } - auto n_rules = slot.allow_ruless.size(); + auto n_rules = slot.allow_rules.size(); if (n_rules > slot.allow_kws.size() + 1) { // one more rules than keyword, last rules do not expire n_rules = slot.allow_kws.size() + 1; - slot.allow_ruless.resize(n_rules); + slot.allow_rules.resize(n_rules); } else if (n_rules < slot.allow_kws.size()) { // every rules expire slot.allow_kws.resize(n_rules); @@ -1728,8 +1728,8 @@ bool server_context::launch_slot_with_task(server_slot& slot, server_task& task) slot.allow_biasess.resize(n_rules); for (size_t i = 0; i < n_rules; ++i) { - const auto& rules = slot.allow_ruless[i]; - if ((i < slot.allow_ruless_prev.size()) && (rules == slot.allow_ruless_prev[i])) { + const auto& rules = slot.allow_rules[i]; + if ((i < slot.allow_rules_prev.size()) && (rules == slot.allow_rules_prev[i])) { continue; } LLAMA_LOG_DEBUG("%s: allowlist %zu is new\n", __func__, i); @@ -1780,7 +1780,7 @@ bool server_context::launch_slot_with_task(server_slot& slot, server_task& task) } } } while (false); - slot.allow_ruless_prev = slot.allow_ruless; + slot.allow_rules_prev = slot.allow_rules; if (llama_model_has_recurrent(llama_get_model(slot.ctx)) || llama_model_is_deepseek4(llama_get_model(slot.ctx))) { params_base.can_ban_phrases = false; @@ -2293,7 +2293,7 @@ void server_context::populate_token_probs(const server_slot& slot, completion_to } } -json server_context::get_formated_generation(const server_slot& slot) const { +json server_context::get_formatted_generation(const server_slot& slot) const { const auto eos_bias = slot.sparams.logit_bias.find(llama_token_eos(model)); const bool ignore_eos = eos_bias != slot.sparams.logit_bias.end() && eos_bias->second < 0.0f && std::isinf(eos_bias->second); @@ -2505,7 +2505,7 @@ void server_context::send_final_response(server_slot& slot) { {"model", params_base.model_alias}, {"tokens_predicted", slot.n_decoded}, {"tokens_evaluated", slot.n_prompt_tokens}, - {"generation_settings", get_formated_generation(slot)}, + {"generation_settings", get_formatted_generation(slot)}, {"prompt", slot.prompt}, {"truncated", slot.truncated}, {"stopped_eos", slot.stopped_eos}, @@ -2513,7 +2513,7 @@ void server_context::send_final_response(server_slot& slot) { {"stopped_limit", slot.stopped_limit}, {"stopping_word", slot.stopping_word}, {"tokens_cached", slot.n_past}, - {"timings", slot.get_formated_timings()}, + {"timings", slot.get_formatted_timings()}, //{"oaicompat_chat_format", slot.params.oaicompat_chat_format}, }; @@ -2851,7 +2851,7 @@ void server_context::process_single_task(server_task&& task) { int n_processing_slots = 0; for (server_slot& slot : slots) { - json slot_data = get_formated_generation(slot); + json slot_data = get_formatted_generation(slot); slot_data["id"] = slot.id; slot_data["id_task"] = slot.id_task; slot_data["state"] = slot.state; diff --git a/examples/server/server-context.h b/examples/server/server-context.h index c6f3d8ee1..551b7d135 100644 --- a/examples/server/server-context.h +++ b/examples/server/server-context.h @@ -105,8 +105,8 @@ struct server_slot { std::map> positional_bans; // allowlist - std::vector>> allow_ruless_prev; - std::vector>> allow_ruless; + std::vector>> allow_rules_prev; + std::vector>> allow_rules; std::vector allow_pieces; std::vector allow_kws; size_t allow_kw_delay = 0; @@ -199,7 +199,7 @@ struct server_slot { void release(); - json get_formated_timings() const; + json get_formatted_timings() const; result_timings get_timings() const; @@ -315,7 +315,7 @@ struct server_context { void populate_token_probs(const server_slot& slot, completion_token_output& result, bool post_sampling, bool special, int idx); - json get_formated_generation(const server_slot& slot) const; + json get_formatted_generation(const server_slot& slot) const; void send_error(const server_task& task, const std::string& error, const enum error_type type = ERROR_TYPE_SERVER); diff --git a/include/llama.h b/include/llama.h index 8b44c889c..fe6e7cf12 100644 --- a/include/llama.h +++ b/include/llama.h @@ -500,8 +500,8 @@ extern "C" { bool only_active_experts; bool prefetch_experts; // if true, stream mmap'd MoE expert weights into the page cache (Linux only) int prefetch_experts_threads; // number of expert prefetch workers (<=0 = auto) - bool k_cache_hadamard; // if true, apply Hadamard transfrom to K-cache - bool v_cache_hadamard; // if true, apply Hadamard transfrom to V-cache (needs FA) + bool k_cache_hadamard; // if true, apply Hadamard transform to K-cache + bool v_cache_hadamard; // if true, apply Hadamard transform to V-cache (needs FA) bool split_mode_graph_scheduling; // if true, force split mode graph scheduling //bool split_mode_f16; // if true, cast intermediate results to f16 before copying to other GPUs bool scheduler_async; // if true, with split mode "graph" graph evaluation will be done using multiple threads @@ -533,8 +533,8 @@ extern "C" { enum ggml_type ffn_gate_type; // feedforward network gate type enum ggml_type ffn_down_type; // feedforward network down type enum ggml_type ffn_up_type; // feedforward network up type - enum ggml_type ffn_gate_inp_type; // routed experts probabilities typy (relevant for MoE models only) - enum ggml_type extra_output_type; // routed experts probabilities typy (relevant for MoE models only) + enum ggml_type ffn_gate_inp_type; // routed experts probabilities type (relevant for MoE models only) + enum ggml_type extra_output_type; // routed experts probabilities type (relevant for MoE models only) bool allow_requantize; // allow quantizing non-f32/f16 tensors bool quantize_output_tensor; // quantize output.weight bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored @@ -1076,7 +1076,7 @@ extern "C" { // Frees a batch of tokens allocated with llama_batch_init() LLAMA_API void llama_batch_free(struct llama_batch batch); - // Processes a batch of tokens with the ecoder part of the encoder-decoder model. + // Processes a batch of tokens with the encoder part of the encoder-decoder model. // Stores the encoder output internally for later use by the decoder cross-attention layers. // 0 - success // < 0 - error @@ -1128,7 +1128,7 @@ extern "C" { // Logits for the ith token. For positive indices, Equivalent to: // llama_get_logits(ctx) + ctx->output_ids[i]*n_vocab - // Negative indicies can be used to access logits in reverse order, -1 is the last logit. + // Negative indices can be used to access logits in reverse order, -1 is the last logit. // returns NULL for invalid ids. LLAMA_API float * llama_get_logits_ith(struct llama_context * ctx, int32_t i); @@ -1146,7 +1146,7 @@ extern "C" { // Get the embeddings for the ith token. For positive indices, Equivalent to: // llama_get_embeddings(ctx) + ctx->output_ids[i]*n_embd - // Negative indicies can be used to access embeddings in reverse order, -1 is the last embedding. + // Negative indices can be used to access embeddings in reverse order, -1 is the last embedding. // shape: [n_embd] (1-dimensional) // returns NULL for invalid ids. LLAMA_API float * llama_get_embeddings_ith(struct llama_context * ctx, int32_t i); @@ -1449,7 +1449,7 @@ extern "C" { LLAMA_API void llama_sampler_reset(struct llama_sampler* smpl); -/// @details Intializes a GBNF grammar, see grammars/README.md for details. +/// @details Initializes a GBNF grammar, see grammars/README.md for details. /// @param vocab The vocabulary that this grammar will be used with. /// @param grammar_str The production rules for the grammar, encoded as a string. Returns an empty grammar if empty. Returns NULL if parsing of grammar_str fails. /// @param grammar_root The name of the start symbol for the grammar. diff --git a/src/graphs/build_gemma3.cpp b/src/graphs/build_gemma3.cpp index 3033acc58..19d7b3270 100644 --- a/src/graphs/build_gemma3.cpp +++ b/src/graphs/build_gemma3.cpp @@ -10,7 +10,7 @@ ggml_cgraph * llm_build_context::build_gemma3() { inpL = llm_build_inp_embd(ctx0, lctx, hparams, batch, model.tok_embd, cb); - // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings) + // important: do not normalize weights for raw embeddings input (i.e. encoded image embeddings) if (batch.token) { inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd)); cb(inpL, "inp_scaled", -1); diff --git a/src/graphs/build_gemma4.cpp b/src/graphs/build_gemma4.cpp index 145a30b15..b8800313b 100644 --- a/src/graphs/build_gemma4.cpp +++ b/src/graphs/build_gemma4.cpp @@ -903,7 +903,7 @@ ggml_cgraph * llm_build_context::build_gemma4() { inpL = llm_build_inp_embd(ctx0, lctx, hparams, batch, model.tok_embd, cb); cb(inpL, "tok_embd", -1); - // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings) + // important: do not normalize weights for raw embeddings input (i.e. encoded image embeddings) if (batch.token) { inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd)); cb(inpL, "inp_scaled", -1); diff --git a/src/graphs/build_mamba.cpp b/src/graphs/build_mamba.cpp index b3ef77c39..7b9aac296 100644 --- a/src/graphs/build_mamba.cpp +++ b/src/graphs/build_mamba.cpp @@ -55,7 +55,7 @@ ggml_cgraph * llm_build_context::build_mamba() { // Custom operator which is needed only to ease simultaneous sequence processing. // For a single sequence, the equivalent is to concatenate the columns of conv_states and x, // then make a self-overlapping view of that over d_conv columns at each stride in the 3rd dimension, - // then element-wise multiply that with the conv1d weigth, + // then element-wise multiply that with the conv1d weight, // then sum the elements of each row, // (the last two steps are a dot product over rows (also doable with mul_mat)) // then permute away the ne[0] dimension, diff --git a/src/llama-build-context.cpp b/src/llama-build-context.cpp index 05409b136..b3c7bdb9d 100644 --- a/src/llama-build-context.cpp +++ b/src/llama-build-context.cpp @@ -2337,7 +2337,7 @@ std::tuple llm_build_context::llm_buil auto [Q, K, V] = llm_build_mul_mat_qkv(gf, cur, wq, bq, wk, bk, wv, bv, attention_scale, il, add_graph_split); auto Qcur = ggml_reshape_3d(ctx0, Q, n_embd_head_k, Q->ne[0]/n_embd_head_k, n_tokens); - // Command-R/R+ uses LayerNorm (not RMSNorm) for per-head Q/K normalisation + // Command-R/R+ uses LayerNorm (not RMSNorm) for per-head Q/K normalization const auto qk_norm_type = (model.arch == LLM_ARCH_COMMAND_R) ? LLM_NORM : LLM_NORM_RMS; if (q_norm) { Qcur = llm_build_norm(ctx0, Qcur, hparams, q_norm, NULL, qk_norm_type, cb, il); diff --git a/src/llama-load-tensors.cpp b/src/llama-load-tensors.cpp index e21aca11f..a6b68d8a2 100644 --- a/src/llama-load-tensors.cpp +++ b/src/llama-load-tensors.cpp @@ -450,7 +450,7 @@ ggml_context * create_tensors_helper::get_context_for_tensor(ggml_context * ctx, if (o.second == default_cpu_buft) has_buft_overrides = true; const struct ggml_tensor * cur = ml.get_tensor_meta(name.c_str()); const size_t nbytes = cur ? ggml_nbytes(cur) : 0; - LLAMA_LOG_INFO("Tensor %s (size = %.2f MiB) buffer type overriden to %s\n", name.c_str(), nbytes/1024./1024., ggml_backend_buft_name(o.second)); + LLAMA_LOG_INFO("Tensor %s (size = %.2f MiB) buffer type overridden to %s\n", name.c_str(), nbytes/1024./1024., ggml_backend_buft_name(o.second)); ctx = ctx_for_buft(o.second); break; } @@ -461,7 +461,7 @@ ggml_context * create_tensors_helper::get_context_for_tensor(ggml_context * ctx, // if (std::regex_search(name, pattern)) { // const struct ggml_tensor * cur = ml.get_tensor_meta(name.c_str()); // const size_t nbytes = cur ? ggml_nbytes(cur) : 0; - // LLAMA_LOG_INFO("Tensor %s (size = %.2f MiB) buffer type overriden to %s\n", name.c_str(), nbytes/1024./1024., ggml_backend_buft_name(overrides->buft)); + // LLAMA_LOG_INFO("Tensor %s (size = %.2f MiB) buffer type overridden to %s\n", name.c_str(), nbytes/1024./1024., ggml_backend_buft_name(overrides->buft)); // ctx = ctx_for_buft(overrides->buft); // break; // } @@ -5392,7 +5392,7 @@ bool create_tensors_helper::create_tensors() { if (model.output) { if (auto it = split_tensors.find(model.output); it != split_tensors.end()) { if (ggml_backend_buft_is_host(model.buft_output.buft_matrix)) { - LLAMA_LOG_INFO("%s: not splitting output tensor becausee buffer is host\n", __func__); + LLAMA_LOG_INFO("%s: not splitting output tensor because buffer is host\n", __func__); } else { auto ctx_split = ctx_map[model.buft_output.buft_matrix]; auto split = create_split(model.output->ne[1], 16, model.splits, mem_used); diff --git a/src/llama-mmap.cpp b/src/llama-mmap.cpp index bbea43058..599a47f76 100644 --- a/src/llama-mmap.cpp +++ b/src/llama-mmap.cpp @@ -574,7 +574,7 @@ struct llama_mlock::impl { char* errmsg = std::strerror(errno); bool suggest = (errno == ENOMEM); #if defined(TARGET_OS_VISION) || defined(TARGET_OS_TV) || defined(_AIX) - // visionOS/tvOS dont't support RLIMIT_MEMLOCK + // visionOS/tvOS don't support RLIMIT_MEMLOCK // Skip resource limit checks on visionOS/tvOS suggest = false; #else diff --git a/src/llama-model.h b/src/llama-model.h index ae1f06e9a..c9bae3103 100644 --- a/src/llama-model.h +++ b/src/llama-model.h @@ -577,7 +577,7 @@ struct llama_model { static inline int hadamard_size(int head_size) { if ((head_size & ~(head_size - 1)) == head_size) return head_size; // Note: we do not include 32 as an option because the CUDA Hadamard implementation - // does not hcurrently andle a block size of 32. + // does not currently handle a block size of 32. for (int i = 512; i >= 64; i >>= 1) { if (head_size % i == 0) return i; } diff --git a/src/llama.cpp b/src/llama.cpp index 5b6515aee..d78920092 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -125,9 +125,6 @@ void llama_set_mtp_n_heads(struct llama_context * ctx, int32_t mtp_n_heads); #pragma warning(disable: 4244 4267) // possible loss of data #endif -// bump if necessary -#define LLAMA_MAX_LAYERS 512 - // // helpers // @@ -807,7 +804,7 @@ int llama_context::max_nodes(int n_tokens, int n_kv) const { model.layers[0].wkv_b) { // In this case we perform the attention computation iteratively, and this adds // 10 nodes per layer per iteration. Although in many cases the 65536 nodes we - // estimate by default are enough to accomodate, to be safe we add the additional + // estimate by default are enough to accommodate, to be safe we add the additional // number of nodes required for the iterative MLA evaluation. int n_head = model.hparams.n_head(); auto wkv_b = model.layers[0].wkv_b; @@ -4836,7 +4833,7 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) { // NOTHING for that sequence and let the (now-)sink token be masked out of top-k, collapsing // it. Anchoring on per-sequence min(pos) keeps the sink protection following the sequence's // actual first present cell. For a fresh sequence starting at pos 0, min(pos)==0 so the - // boosted set is identical to the old behaviour (n_seq==1 byte-identical). + // boosted set is identical to the old behavior (n_seq==1 byte-identical). GGML_ASSERT(ggml_backend_buffer_is_host(lctx.inp_dsa_sink->buffer)); static const int n_sink = []{ const char * e = getenv("DSA_SINK"); return e ? atoi(e) : 1; }(); const int64_t n_kv = lctx.inp_dsa_sink->ne[0]; diff --git a/tests/test-chat.cpp b/tests/test-chat.cpp index 0e3c412ca..900fa87d0 100644 --- a/tests/test-chat.cpp +++ b/tests/test-chat.cpp @@ -4277,7 +4277,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) { }, "replaceAll": { "type": "boolean", - "description": "Whether to replace all occurences." + "description": "Whether to replace all occurrences." } }, "required": ["oldString", "newString"] diff --git a/vendor/stb/stb_image_resize2.h b/vendor/stb/stb_image_resize2.h index 079897658..51963b2c3 100644 --- a/vendor/stb/stb_image_resize2.h +++ b/vendor/stb/stb_image_resize2.h @@ -6772,7 +6772,7 @@ static void stbir__get_split_info( stbir__per_split_info* split_info, int splits // simply bump up our previous thread split range to include it, and then start this threads // range with the smaller sample. It just moves one scanline from one thread split to another, // so that we end with the unusual one, instead of start with it. To do this, we check 2-4 - // sample at each thread split start and then occassionally move them. + // sample at each thread split start and then occasionally move them. if ( ( is_gather ) && ( i ) ) {