Files
project_6/vllm
muh d70deefae1 [ENGINE] sampler.py: CCCL bit_packed_counter documentation + cache retention
Reference catch2_test_memcpy_bitpacked_counter.cu bit packing pattern.
Maintain int64 dtype (scatter_add_ CUDA requirement) but document the
future optimization path to int16 (4x memory reduction when supported).
Pre-allocation caching already in place from prior commit.
2026-08-06 01:00:46 +00:00
..