mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-14 20:29:41 -04:00
fd1234cb46
* oai moe * compat with new checkpoint * add attn sink impl * add rope scaling yarn * logits match with latest transformers code * wip chat template * rm trailing space * use ggml_scale_bias * rm redundant is_swa_all * convert interleaved gate_up * graph : fix activation function to match reference (#7) * vocab : handle o200k_harmony special tokens * ggml : add attention sinks support (#1) * llama : add attn sinks * ggml : add attn sinks * cuda : add attn sinks * vulkan : add support for sinks in softmax remove unnecessary return * ggml : add fused swiglu_oai op (#11) * ggml : add fused swiglu_oai op * Update ggml/src/ggml-cpu/ops.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * update CUDA impl * cont : metal impl * add vulkan impl * test-backend-ops : more test cases, clean up * llama : remove unfused impl * remove extra lines --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: slaren <slarengh@gmail.com> * repack mxfp4 upon conversion * clean up a bit * enable thinking * add quick hack to render only some special tokens * fix bf16 conversion * remove vocab hack * webui ok * support chat parsing for gpt-oss * fix webui * direct mapping mxfp4, FINALLY * force using mxfp4 * properly use lazy tensor * ggml : add mxfp4 ggml : use e8m0 conversion instead of powf Co-authored-by: Diego Devesa <slarengh@gmail.com> change kvalues_mxfp4 table to match e2m1 (#6) metal : remove quantization for now (not used) cuda : fix disabled CUDA graphs due to ffn moe bias vulkan : add support for mxfp4 cont : add cm2 dequant * ggml : add ggml_add_id (#13) * ggml : add ggml_add_id * add cuda impl * llama : add weight support check for add_id * perf opt * add vulkan impl * rename cuda files * add metal impl * allow in-place ggml_add_id * llama : keep biases on CPU with --cpu-moe * llama : fix compile error ggml-ci * cuda : add fallback for __nv_cvt_e8m0_to_bf16raw ggml-ci * cleanup ggml-ci * sycl : fix supports_op for MXFP4 ggml-ci * fix Unknown reasoning format * ggml-cpu : fix AVX build ggml-ci * fix hip build ggml-ci * cuda : add mxfp4 dequantization support for cuBLAS ggml-ci * ggml-cpu : fix mxfp4 fallback definitions for some architectures ggml-ci * cuda : fix version required for __nv_cvt_e8m0_to_bf16raw --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: slaren <slarengh@gmail.com>
65 lines
1.9 KiB
C++
65 lines
1.9 KiB
C++
#pragma once
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
#include <cstdint>
|
|
|
|
enum llm_chat_template {
|
|
LLM_CHAT_TEMPLATE_CHATML,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_BOS,
|
|
LLM_CHAT_TEMPLATE_LLAMA_2_SYS_STRIP,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V1,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V3_TEKKEN,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V7,
|
|
LLM_CHAT_TEMPLATE_MISTRAL_V7_TEKKEN,
|
|
LLM_CHAT_TEMPLATE_PHI_3,
|
|
LLM_CHAT_TEMPLATE_PHI_4,
|
|
LLM_CHAT_TEMPLATE_FALCON_3,
|
|
LLM_CHAT_TEMPLATE_ZEPHYR,
|
|
LLM_CHAT_TEMPLATE_MONARCH,
|
|
LLM_CHAT_TEMPLATE_GEMMA,
|
|
LLM_CHAT_TEMPLATE_ORION,
|
|
LLM_CHAT_TEMPLATE_OPENCHAT,
|
|
LLM_CHAT_TEMPLATE_VICUNA,
|
|
LLM_CHAT_TEMPLATE_VICUNA_ORCA,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_2,
|
|
LLM_CHAT_TEMPLATE_DEEPSEEK_3,
|
|
LLM_CHAT_TEMPLATE_COMMAND_R,
|
|
LLM_CHAT_TEMPLATE_LLAMA_3,
|
|
LLM_CHAT_TEMPLATE_CHATGLM_3,
|
|
LLM_CHAT_TEMPLATE_CHATGLM_4,
|
|
LLM_CHAT_TEMPLATE_GLMEDGE,
|
|
LLM_CHAT_TEMPLATE_MINICPM,
|
|
LLM_CHAT_TEMPLATE_EXAONE_3,
|
|
LLM_CHAT_TEMPLATE_EXAONE_4,
|
|
LLM_CHAT_TEMPLATE_RWKV_WORLD,
|
|
LLM_CHAT_TEMPLATE_GRANITE,
|
|
LLM_CHAT_TEMPLATE_GIGACHAT,
|
|
LLM_CHAT_TEMPLATE_MEGREZ,
|
|
LLM_CHAT_TEMPLATE_YANDEX,
|
|
LLM_CHAT_TEMPLATE_BAILING,
|
|
LLM_CHAT_TEMPLATE_LLAMA4,
|
|
LLM_CHAT_TEMPLATE_SMOLVLM,
|
|
LLM_CHAT_TEMPLATE_DOTS1,
|
|
LLM_CHAT_TEMPLATE_HUNYUAN_MOE,
|
|
LLM_CHAT_TEMPLATE_OPENAI_MOE,
|
|
LLM_CHAT_TEMPLATE_HUNYUAN_DENSE,
|
|
LLM_CHAT_TEMPLATE_KIMI_K2,
|
|
LLM_CHAT_TEMPLATE_UNKNOWN,
|
|
};
|
|
|
|
struct llama_chat_message;
|
|
|
|
llm_chat_template llm_chat_template_from_str(const std::string & name);
|
|
|
|
llm_chat_template llm_chat_detect_template(const std::string & tmpl);
|
|
|
|
int32_t llm_chat_apply_template(
|
|
llm_chat_template tmpl,
|
|
const std::vector<const llama_chat_message *> & chat,
|
|
std::string & dest, bool add_ass);
|