llama.cpp / convert-llama-ggml-to-gguf.py convert-llama-ggml-to-gguf.py 18.29 KB 一键复制 编辑 原始数据 按行查看 历史 Jared Van Bortel 提交于 1年前 . convert : automatically fall back to HfVocab if tokenizer.model doesn'… 1234567891011121314151617181920212223242526272829303132333435363738394...
gguf.MODEL_ARCH_NAMES[gguf.MODEL_ARCH.LLAMA], use_temp_file = False) self.add_params(gguf_writer) self.add_vocab(gguf_writer) if self.special_vocab is not None: self.special_vocab.add_to_gguf(gguf_writer) self.add_tensors(gguf_writer) logger.info(" gguf: write heade...
/home/wanli/workspace/llama.cpp/ggml/src/ggml-aarch64.c:47:54: error: incompatible type for argument 1 of ‘_mm512_cvtph_ps’ #define GGML_F32Cx8x2_LOAD(x, y) _mm512_cvtph_ps(_mm256_set_m128i(_mm_loadu_si128((const __m128i *)(y)), _mm_loadu_si128((const __m128...
/home/warehouse/llmfn/llama.cpp-master/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp:80:54: error: ‘_mm256_set_m128i’ was not declaredinthis scope#define GGML_F32Cx8x2_LOAD(x, y) _mm512_cvtph_ps(_mm256_set_m128i(_mm_loadu_si128((const __m128i *)(y)), _mm_loadu_si128...
Git commit Bug Description I encountered a build error while compiling llama.cpp in a VirtualBox environment (Ubuntu 20.04). The issue occurs in ggml-cpu-aarch64.cpp, where an invalid conversion error is triggered. It seems that AArch64-...
ggml-aarch64.c ggml-aarch64.h ggml-cann ggml-cann.cpp ggml-common.h ggml-cpu CMakeLists.txt amx amx.cpp amx.h common.h mmq.cpp mmq.h ggml-cpu-aarch64.cpp ggml-cpu-aarch64.h ggml-cpu-hbm.cpp ggml-cpu-hbm.h ggml-cpu-traits.cpp ggml-cpu-tra...
EditorConfig Checker ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064) #22281 Sign in to view logs Summary Jobs editorconfig Run details Usage Workflow file Triggered via push February 28, 2025 07:36 ggerganov pushed 05e6f5a master ...
mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025 ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (ggml-o… … 846f7ed Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment ...
我电脑上的实验数据，配置是 TR-3970x 和 RTX3080Ti Whisper Medium + PyTorch CPU： 每小时音频需要...
速度相近，所以PyTorch其实适合GPU训练，并不适合CPU训练和推理，如果只推理且用CPU的话，建议使用优化程度...