Lucas Wilkinson 8bdc70ec7b [6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

2026-08-21 17:47:49 -07:00

..

__init__.py

…

argparse_utils.py

…

async_utils.py

…

b12x.py

[Kernel] Add b12x FP4 MoE backend (#52018)

2026-08-21 08:04:36 -07:00

cache.py

[Bugfix] Skip MM processor cache inserts larger than capacity (#53016)

2026-08-20 13:42:50 +00:00

collection_utils.py

…

counter.py

[Misc] Separate out utils.counter and move utils.Device to engine (#27588)

2025-10-28 12:20:46 +00:00

cpu_resource_utils.py

…

cpu_triton_utils.py

…

deep_gemm.py

…

flashinfer.py

[Kernel] Add FlashInfer TRTLLM MXFP8 linear backend (#52204)

2026-08-20 10:07:22 -04:00

func_utils.py

…

gc_utils.py

…

gpu_sync_debug.py

…

hashing.py

…

hpc.py

…

humming.py

…

import_utils.py

…

jit_monitor.py

…

jsontree.py

…

math_utils.py

…

mem_constants.py

…

mem_utils.py

…

mistral.py

…

multi_stream_utils.py

…

nccl.py

…

network_utils.py

…

numa_utils.py

…

numa_wrapper.sh

[CI] replace shellcheck script with shellcheck-py hook (#52572)

2026-08-20 10:09:59 +00:00

nvtx_pytorch_hooks.py

…

ompmultiprocessing.py

…

platform_utils.py

…

print_utils.py

…

registry.py

…

serial_utils.py

…

sparse_utils.py

…

system_utils.py

…

tensor_schema.py

…

torch_utils.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

tqdm_utils.py

[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)

2026-02-17 05:29:01 -08:00