full-cuda.Dockerfile
Commit
284 days ago
Author
Committer
- Files395
- .devops
- full-rocm.Dockerfile
- full.Dockerfile
- llama-cli-cann.Dockerfile
- llama-cli-cuda.Dockerfile
- llama-cli-intel.Dockerfile
- llama-cli-rocm.Dockerfile
- llama-cli-vulkan.Dockerfile
- llama-cli.Dockerfile
- llama-server-cuda.Dockerfile
- llama-server-intel.Dockerfile
- llama-server-rocm.Dockerfile
- llama-server-vulkan.Dockerfile
- llama-server.Dockerfile
- nix
apps.nix- package.nix
tools.sh
- .ecrc
- .github
labeler.yml- workflows
- bench.yml.disabled
- build.yml
- docker.yml
- python-check-requirements.yml
- python-type-check.yml
.gitignore
CMakeLists.txt
CMakePresets.json
CONTRIBUTING.md
Makefile
Package.swift
README.md- ci
- run.sh
- cmake
- llama-config.cmake.in
- common
common.cpp
common.h- grammar-parser.cpp
- log.h
- ngram-cache.h
- sampling.cpp
- stb_image.h
convert_hf_to_gguf.py- convert_hf_to_gguf_update.py
- convert_llama_ggml_to_gguf.py
- convert_lora_to_gguf.py
- docs
android.md- backend
- BLIS.md
- CANN.md
- SYCL.md
- build.md
- development
- HOWTO-add-model.md
- debugging-tests.md
- llama-star
idea-arch.key
idea-arch.pdf
- token_generation_performance_tips.md
- docker.md
- install.md
- examples
- CMakeLists.txt
- baby-llama
- baby-llama.cpp
- batched-bench
- batched-bench.cpp
- batched.swift/Sources
- main.swift
- batched
- batched.cpp
- benchmark
- benchmark-matmult.cpp
- convert_legacy_llama.py
- cvector-generator
- cvector-generator.cpp
- deprecation-warning
- README.md
- deprecation-warning.cpp
- embedding
- README.md
- embedding.cpp
- eval-callback
- eval-callback.cpp
- export-lora
- README.md
- export-lora.cpp
- finetune
- CMakeLists.txt
- README.md
- convert-finetune-checkpoint-to-gguf.py
- finetune.cpp
- finetune.sh
- gbnf-validator
- gbnf-validator.cpp
- gguf-hash
- CMakeLists.txt
- README.md
- deps
- rotate-bits
package.json- rotate-bits.h
- sha1
- package.json
sha1.c- sha1.h
- sha256
- package.json
- sha256.c
- sha256.h
- xxhash
- clib.json
- xxhash.c
- xxhash.h
- gguf-hash.cpp
- gguf
- gguf.cpp
- imatrix
- README.md
- imatrix.cpp
- infill
- infill.cpp
- json_schema_pydantic_example.py
- json_schema_to_grammar.py
- llama-bench
- llama-bench.cpp
- llama.android/llama/src/main/cpp
- llama-android.cpp
- llama.swiftui
- llama.cpp.swift
- LibLlama.swift
- llama.swiftui/Models
- LlamaState.swift
- llava
- CMakeLists.txt
- MobileVLM-README.md
- README-minicpmv2.5.md
- README-minicpmv2.6.md
- README.md
- clip.cpp
- clip.h
- convert_image_encoder_to_gguf.py
- llava-cli.cpp
- llava.cpp
- llava.h
- llava_surgery.py
- llava_surgery_v2.py
- minicpmv-cli.cpp
- minicpmv-convert-image-encoder-to-gguf.py
- minicpmv-surgery.py
requirements.txt
- lookahead
- lookahead.cpp
- lookup
- lookup-create.cpp
- lookup-stats.cpp
- lookup.cpp
- main
- README.md
- main.cpp
- parallel
- parallel.cpp
- passkey
- README.md
- perplexity
- perplexity.cpp
- pydantic-models-to-grammar-examples.py
- pydantic_models_to_grammar.py
- pydantic_models_to_grammar_examples.py
- quantize-stats
- quantize-stats.cpp
- quantize
- README.md
- quantize.cpp
- regex_to_grammar.py
- retrieval
- retrieval.cpp
- rpc
- README.md
- rpc-server.cpp
- save-load-state
- save-load-state.cpp
- server
- README.md
- bench
- bench.py
- public
completion.js
index-new.html- index.html
- index.js
- server.cpp
- tests
- features
lora.feature- steps
- steps.py
- requirements.txt
utils.hpp
- server_embd.py
- simple
- README.md
- speculative
- speculative.cpp
- sycl
- README.md
- win-run-llama2.bat
- tokenize
- tokenize.cpp
- train-text-from-scratch
- CMakeLists.txt
- README.md
- convert-train-checkpoint-to-gguf.py
- train-text-from-scratch.cpp
flake.lock- ggml
- .gitignore
- CMakeLists.txt
- ggml_vk_generate_shaders.py
- include
- ggml-alloc.h
- ggml-backend.h
- ggml-cann.h
- ggml-cuda.h
- ggml-metal.h
- ggml.h
- src
- CMakeLists.txt
- ggml-aarch64.c
- ggml-aarch64.h
- ggml-alloc.c
- ggml-backend.c
- ggml-blas.cpp
- ggml-cann.cpp
- ggml-cann
.clang-format- Doxyfile
- acl_tensor.cpp
- acl_tensor.h
- aclnn_ops.cpp
- aclnn_ops.h
- common.h
- kernels
- CMakeLists.txt
- ascendc_kernels.h
- dup.cpp
- get_row_f16.cpp
- get_row_f32.cpp
- get_row_q4_0.cpp
- get_row_q8_0.cpp
- quantize_f16_q8_0.cpp
- quantize_f32_q8_0.cpp
- quantize_float_to_q4_0.cpp
- ggml-common.h
ggml-cuda.cu- ggml-cuda
- argsort.cu
- binbcast.cu
- binbcast.cuh
- common.cuh
- conv-transpose-1d.cu
- conv-transpose-1d.cuh
- cpy.cu
- cross-entropy-loss.cu
- cross-entropy-loss.cuh
- dmmv.cu
- dmmv.cuh
- fattn-common.cuh
- fattn-tile-f16.cu
- fattn-tile-f32.cu
- fattn-vec-f16.cuh
- fattn-vec-f32.cuh
- fattn-wmma-f16.cuh
- fattn.cu
- getrows.cu
- mma.cuh
- mmq.cu
- mmq.cuh
- mmvq.cu
- norm.cu
- quantize.cu
- quantize.cuh
- rope.cu
- sumrows.cu
- sumrows.cuh
- template-instances
- generate_cu_files.py
- mmq-instance-iq1_s.cu
- mmq-instance-iq2_s.cu
- mmq-instance-iq2_xs.cu
- mmq-instance-iq2_xxs.cu
- mmq-instance-iq3_s.cu
- mmq-instance-iq3_xxs.cu
- mmq-instance-iq4_nl.cu
- mmq-instance-iq4_xs.cu
- unary.cu
- unary.cuh
- vecdotq.cuh
- vendors
- cuda.h
- hip.h
- musa.h
- ggml-impl.h
- ggml-kompute.cpp
ggml-metal.m- ggml-metal.metal
- ggml-quants.c
- ggml-quants.h
- ggml-rpc.cpp
- ggml-sycl.cpp
- ggml-sycl
- backend.hpp
- common.cpp
- common.hpp
- concat.cpp
- concat.hpp
- conv.cpp
- conv.hpp
- convert.cpp
- convert.hpp
- dequantize.hpp
- dmmv.cpp
- dpct
- helper.hpp
- gemm.hpp
- im2col.cpp
- im2col.hpp
- mmq.cpp
- mmvq.cpp
- norm.cpp
- presets.hpp
- rope.cpp
- softmax.cpp
- softmax.hpp
- tsembd.cpp
- tsembd.hpp
- ggml-vulkan-shaders.hpp
- ggml-vulkan.cpp
- ggml.c
- kompute-shaders
op_rope_f16.comp- op_rope_f32.comp
- rope_common.comp
- llamafile
- sgemm.cpp
- sgemm.h
- vulkan-shaders
- CMakeLists.txt
- acc.comp
- add.comp
- clamp.comp
- concat.comp
- copy.comp
- cos.comp
- dequant_funcs.comp
- dequant_iq4_nl.comp
- dequant_q4_0.comp
- div.comp
- gelu.comp
- gelu_quick.comp
- generic_binary_head.comp
- generic_unary_head.comp
- group_norm.comp
- im2col.comp
- leaky_relu.comp
- mul.comp
- mul_mat_vec.comp
- mul_mat_vec_nc.comp
- mul_mat_vec_p021.comp
- mul_mat_vec_q2_k.comp
- mul_mat_vec_q3_k.comp
- mul_mat_vec_q4_k.comp
- mul_mat_vec_q5_k.comp
- mul_mat_vec_q6_k.comp
- mul_mm.comp
- norm.comp
- pad.comp
- relu.comp
- repeat.comp
- rms_norm.comp
- scale.comp
- silu.comp
- sin.comp
- soft_max.comp
- square.comp
- sum_rows.comp
- tanh.comp
- timestep_embedding.comp
- types.comp
- upscale.comp
- vulkan-shaders-gen.cpp
- gguf-py
- README.md
- examples
- writer.py
- gguf
- __init__.py
- constants.py
- gguf_reader.py
- gguf_writer.py
- lazy.py
- metadata.py
- quants.py
- tensor_mapping.py
- utility.py
- pyproject.toml
- scripts
- __init__.py
- gguf_convert_endian.py
- gguf_dump.py
- gguf_hash.py
- gguf_new_metadata.py
- gguf_set_metadata.py
- tests
- __init__.py
- test_gguf.py
- test_metadata.py
- test_quants.py
- grammars
- README.md
- include
- llama.h
- models
- ggml-vocab-gpt2.gguf
- ggml-vocab-stablelm.gguf
- pyrightconfig.json
- requirements.txt
- requirements
requirements-all.txt- requirements-compare-llama-bench.txt
- requirements-convert_hf_to_gguf.txt
- requirements-convert_hf_to_gguf_update.txt
- requirements-convert_legacy_llama.txt
- requirements-convert_llama_ggml_to_gguf.txt
- requirements-convert_lora_to_gguf.txt
- requirements-pydantic.txt
- requirements-test-tokenizer-random.txt
- scripts
- check-requirements.sh
- compare-llama-bench.py
- convert-gg.sh
- gen-unicode-data.py
- pod-llama.sh
- sync-ggml-am.sh
- sync-ggml.last
- sync-ggml.sh
- src
- CMakeLists.txt
- llama-grammar.cpp
- llama-grammar.h
- llama-impl.h
- llama-sampling.cpp
- llama-sampling.h
- llama-vocab.cpp
- llama-vocab.h
- llama.cpp
- unicode.cpp
- unicode.h
- tests
- CMakeLists.txt
- test-backend-ops.cpp
- test-chat-template.cpp
- test-double-float.cpp
- test-grad0.cpp
- test-grammar-integration.cpp
- test-llama-grammar.cpp
- test-lora-conversion-inference.sh
- test-quantize-fns.cpp
- test-quantize-perf.cpp
- test-rope.cpp
- test-sampling.cpp
- test-tokenizer-0.cpp
- test-tokenizer-1-bpe.cpp
- test-tokenizer-1-spm.cpp
- test-tokenizer-random.py