.envrc
.gitignore
.markdownlint-cli2.yaml
.pre-commit-config.yaml
CODEOWNERS
LICENSE
README.md
pyproject.toml
setup.py
.github/CODEOWNERS
.github/pull_request_template.md
benchmarks/bnb_dequantize_blockwise_benchmark.py
benchmarks/bnb_quantize_blockwise_benchmark.py
benchmarks/copy_blocks_benchmark.py
benchmarks/fused_add_rms_norm_benchmark.py
benchmarks/gelu_tanh_and_mul_benchmark.py
benchmarks/gemma_rms_norm_benchmark.py
benchmarks/mixed_precision_gemm_benchmark.py
benchmarks/paged_attention_benchmark.py
benchmarks/paged_attention_vs_flash_benchmark.py
benchmarks/reshape_and_cache_benchmark.py
benchmarks/rms_norm_benchmark.py
benchmarks/rotary_embedding_benchmark.py
benchmarks/scaled_gemm_benchmark.py
benchmarks/silu_and_mul_benchmark.py
benchmarks/static_scaled_fp8_quant_benchmark.py
benchmarks/static_scaled_int8_quant_benchmark.py
benchmarks/varlen_attention_benchmark.py
conch/README.md
conch/__init__.py
conch/_version.py
conch/envs.py
conch/kernels/activation/__init__.py
conch/kernels/activation/gelu_tanh_and_mul.py
conch/kernels/activation/silu_and_mul.py
conch/kernels/attention/__init__.py
conch/kernels/attention/paged_attention.py
conch/kernels/attention/varlen_attention.py
conch/kernels/embedding/__init__.py
conch/kernels/embedding/rotary_embedding.py
conch/kernels/normalization/__init__.py
conch/kernels/normalization/gemma_rms_norm.py
conch/kernels/normalization/rms_norm.py
conch/kernels/quantization/__init__.py
conch/kernels/quantization/fp8.py
conch/kernels/quantization/gemm.py
conch/kernels/quantization/int8.py
conch/kernels/quantization/bitsandbytes/__init__.py
conch/kernels/quantization/bitsandbytes/dequantize_blockwise.py
conch/kernels/quantization/bitsandbytes/quantize_blockwise.py
conch/kernels/vllm/__init__.py
conch/kernels/vllm/copy_blocks.py
conch/kernels/vllm/reshape_and_cache.py
conch/ops/activation/__init__.py
conch/ops/activation/gelu_tanh_and_mul.py
conch/ops/activation/silu_and_mul.py
conch/ops/attention/__init__.py
conch/ops/attention/paged_attention.py
conch/ops/attention/varlen_attention.py
conch/ops/embedding/__init__.py
conch/ops/embedding/rotary_embedding.py
conch/ops/normalization/__init__.py
conch/ops/normalization/gemma_rms_norm.py
conch/ops/normalization/rms_norm.py
conch/ops/quantization/__init__.py
conch/ops/quantization/fp8.py
conch/ops/quantization/gemm.py
conch/ops/quantization/int8.py
conch/ops/quantization/bitsandbytes/__init__.py
conch/ops/quantization/bitsandbytes/functional.py
conch/ops/vllm/__init__.py
conch/ops/vllm/copy_blocks.py
conch/ops/vllm/reshape_and_cache.py
conch/platforms/__init__.py
conch/platforms/platform.py
conch/reference/activation/__init__.py
conch/reference/activation/gelu_tanh_and_mul.py
conch/reference/activation/silu_and_mul.py
conch/reference/embedding/__init__.py
conch/reference/embedding/rotary_embedding.py
conch/reference/normalization/__init__.py
conch/reference/normalization/gemma_rms_norm.py
conch/reference/normalization/rms_norm.py
conch/reference/quantization/__init__.py
conch/reference/quantization/fp8.py
conch/reference/quantization/int8.py
conch/reference/quantization/scaled_gemm.py
conch/reference/quantization/bitsandbytes/__init__.py
conch/reference/quantization/bitsandbytes/dequantize_blockwise.py
conch/reference/quantization/bitsandbytes/quantize_blockwise.py
conch/reference/vllm/__init__.py
conch/reference/vllm/copy_blocks.py
conch/reference/vllm/reshape_and_cache.py
conch/third_party/vllm/__init__.py
conch/third_party/vllm/quant_utils.py
conch/third_party/vllm/scalar_type.py
conch/third_party/vllm/unified_attention.py
conch/third_party/vllm/utils.py
conch/utils/__init__.py
conch/utils/benchmark.py
conch_triton_kernels.egg-info/PKG-INFO
conch_triton_kernels.egg-info/SOURCES.txt
conch_triton_kernels.egg-info/dependency_links.txt
conch_triton_kernels.egg-info/requires.txt
conch_triton_kernels.egg-info/top_level.txt
docs/conch/structure.md
docs/conch/triton.md
docs/development/contributing.md
docs/development/coverage.md
docs/development/linting.md
docs/distribution/wheel.md
docs/getting_started/developer_environment.md
docs/getting_started/installation.md
docs/performance/bitsandbytes.md
docs/repo/structure.md
tests/copy_blocks_test.py
tests/dequantize_blockwise_test.py
tests/fp8_quant_kernels_test.py
tests/gelu_tanh_and_mul_test.py
tests/gemma_rms_norm_test.py
tests/int8_quant_kernels_test.py
tests/mixed_precision_gemm_test.py
tests/paged_attention_test.py
tests/quantize_blockwise_test.py
tests/reshape_and_cache_test.py
tests/rms_norm_test.py
tests/rotary_embedding_test.py
tests/scaled_gemm_test.py
tests/silu_and_mul_test.py
tests/varlen_attention_test.py
tools/create_benchmark_results_table.py
tools/mypy.sh
tools/plot_benchmark_results.py
tools/benchmarks/collect_copy_blocks.sh
tools/benchmarks/collect_paged_attention_vs_flash.sh
tools/benchmarks/collect_reshape_and_cache.sh
tools/benchmarks/collect_varlen_attention_decode.sh
tools/benchmarks/collect_varlen_attention_prefill.sh
tools/benchmarks/run_all.sh
tools/env/direnv.sh
tools/wheel/build.sh