CMakeLists.txt
LICENSE
MANIFEST.in
README.md
pyproject.toml
setup.py
csrc/bindings/pybind.cpp
csrc/cpu/fp32_ops.c
csrc/cpu/gguf_writer.c
csrc/cpu/offload.cpp
csrc/cpu/quantize.c
csrc/gpu/cross_attention.cu
csrc/gpu/memory_manager.cpp
csrc/gpu/projector_kernel.cu
csrc/gpu/projector_kernel.cuh
csrc/gpu/streams.cpp
csrc/gpu/vision_pack.cu
csrc/gpu/vq_lookup.cu
csrc/tpu/jax_ops.py
csrc/tpu/xla_backend.cpp
openllava/__init__.py
openllava.egg-info/PKG-INFO
openllava.egg-info/SOURCES.txt
openllava.egg-info/dependency_links.txt
openllava.egg-info/entry_points.txt
openllava.egg-info/requires.txt
openllava.egg-info/top_level.txt
openllava/api/__init__.py
openllava/api/callbacks.py
openllava/api/config.py
openllava/api/fast_model.py
openllava/api/loggers.py
openllava/api/strategies.py
openllava/api/trainer.py
openllava/backends/__init__.py
openllava/backends/cpu_simd.py
openllava/backends/gguf_v2.py
openllava/backends/mlx_backend.py
openllava/backends/onnx_export.py
openllava/backends/rocm_backend.py
openllava/backends/safetensors_io.py
openllava/backends/tpu_dataloader.py
openllava/backends/tpu_spmd.py
openllava/backends/tpu_xla.py
openllava/backends/xpu_backend.py
openllava/cli/__init__.py
openllava/cli/main.py
openllava/cli/commands/__init__.py
openllava/cli/commands/benchmark.py
openllava/cli/commands/export.py
openllava/cli/commands/serve.py
openllava/cli/commands/train.py
openllava/core/__init__.py
openllava/core/backend.py
openllava/core/model.py
openllava/core/patcher.py
openllava/data/__init__.py
openllava/data/collator.py
openllava/data/gpu_augmentation.py
openllava/data/pipeline.py
openllava/data/preprocessing.py
openllava/data/smart_batching.py
openllava/data/streaming.py
openllava/data/templates.py
openllava/distributed/__init__.py
openllava/distributed/auto_parallel.py
openllava/distributed/cluster_config.py
openllava/distributed/deepspeed.py
openllava/distributed/device_mesh.py
openllava/distributed/dtensor_ops.py
openllava/distributed/expert_parallel.py
openllava/distributed/fsdp.py
openllava/distributed/heterogeneous.py
openllava/distributed/init_process.py
openllava/distributed/parallel_4d.py
openllava/distributed/pipeline_parallel.py
openllava/distributed/placement.py
openllava/distributed/ring_attention.py
openllava/distributed/tensor_parallel.py
openllava/distributed/topology.py
openllava/distributed/zero_hpz.py
openllava/distributed/zero_offload.py
openllava/eval/__init__.py
openllava/eval/mmbench.py
openllava/eval/runner.py
openllava/eval/scienceqa.py
openllava/eval/textvqa.py
openllava/experts/__init__.py
openllava/experts/moe_layers.py
openllava/experts/moe_lora.py
openllava/experts/moe_trainer.py
openllava/experts/ocr.py
openllava/experts/router.py
openllava/experts/visual.py
openllava/export/__init__.py
openllava/export/gguf.py
openllava/export/hub.py
openllava/export/merge.py
openllava/export/quantize.py
openllava/inference/__init__.py
openllava/inference/continuous_batching.py
openllava/inference/engine.py
openllava/inference/paged_attention.py
openllava/inference/speculative_decoding.py
openllava/kernels/__init__.py
openllava/kernels/streams.py
openllava/kernels/cuda_graphs/__init__.py
openllava/kernels/cuda_graphs/graph_trainer.py
openllava/kernels/triton/__init__.py
openllava/kernels/triton/bitnet_gemm.py
openllava/kernels/triton/blindsight.py
openllava/kernels/triton/flash_attention.py
openllava/kernels/triton/flex_attention.py
openllava/kernels/triton/fused_attention.py
openllava/kernels/triton/fused_cross_entropy.py
openllava/kernels/triton/fused_projector.py
openllava/kernels/triton/fused_rmsnorm.py
openllava/kernels/triton/fused_rope.py
openllava/kernels/triton/fused_swiglu.py
openllava/kernels/triton/grouped_gemm.py
openllava/kernels/triton/online_softmax.py
openllava/kernels/triton/sparse_attention.py
openllava/optimizations/__init__.py
openllava/optimizations/async_io.py
openllava/optimizations/bitnet.py
openllava/optimizations/bitnet_a48.py
openllava/optimizations/chunked_prefill.py
openllava/optimizations/cpu_offload.py
openllava/optimizations/curriculum.py
openllava/optimizations/eagle_draft.py
openllava/optimizations/ema.py
openllava/optimizations/fast_nf4.py
openllava/optimizations/fp4_quant.py
openllava/optimizations/fp8_training.py
openllava/optimizations/full_finetune.py
openllava/optimizations/galore.py
openllava/optimizations/gptq_awq.py
openllava/optimizations/kv_compression.py
openllava/optimizations/kv_eviction.py
openllava/optimizations/kv_quantization.py
openllava/optimizations/medusa_heads.py
openllava/optimizations/memory_pool.py
openllava/optimizations/mixed_precision_quant.py
openllava/optimizations/mxfp8_moe.py
openllava/optimizations/ngram_draft.py
openllava/optimizations/packing.py
openllava/optimizations/padding_free.py
openllava/optimizations/qat.py
openllava/optimizations/schedulers.py
openllava/optimizations/selective_checkpoint.py
openllava/optimizations/sparse_attn_selector.py
openllava/optimizations/split_lora.py
openllava/optimizations/torch_compile.py
openllava/optimizations/torchao_integration.py
openllava/optimizations/tree_verification.py
openllava/optimizations/yadis_cross_attn.py
openllava/optimizations/yadis_moe_adaptive.py
openllava/optimizations/yadis_vq_ema.py
openllava/rl/__init__.py
openllava/rl/dpo.py
openllava/rl/grpo.py
openllava/rl/orpo.py
openllava/rl/ppo.py
openllava/rl/rewards.py
openllava/rl/vllm_integration.py
openllava/serve/__init__.py
openllava/serve/batch_manager.py
openllava/serve/metrics.py
openllava/serve/middleware.py
openllava/serve/openai_api.py
openllava/serve/server.py
openllava/training/__init__.py
openllava/training/bitnet_trainer.py
openllava/training/checkpointing.py
openllava/training/dora.py
openllava/training/lora.py
openllava/training/lora_fa.py
openllava/training/lora_ga.py
openllava/training/lora_plus.py
openllava/training/lora_registry.py
openllava/training/memory.py
openllava/training/trainer.py
openllava/utils/__init__.py
openllava/utils/auto_detect.py
openllava/utils/benchmark.py
openllava/utils/hardware_detect.py
openllava/utils/hub.py
openllava/utils/model_card.py
openllava/utils/profiler.py
openllava/utils/registry.py