whn09 fb9dea85cb Neuron sampler: skip the top-p/top-k bisection when no row filters (#27) ... The bisection is 32 rounds over the vocabulary: ~0.5 s a decode step at 129280 even compiled, and the default parameters (top_p 1, top_k -1) filter nothing. Such batches take the plain temperature log-softmax: 529.6 -> 1.3 ms on one core, same tokens, logprobs within 1e-9. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 12:05:16 +08:00
..
tilelang_ops	Neuron sampler: skip the top-p/top-k bisection when no row filters (#27)	2026-10-23 12:05:16 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
attention_backend.py	initial commit	2026-10-20 12:09:42 +08:00
layernorm.py	initial commit	2026-10-20 12:09:42 +08:00
linear.py	Neuron: per-layer region graphs + vllm-neuron#71 NKI kernels (issues #10, #11, #13, #25)	2026-10-22 17:36:54 +08:00
mtp_info_pool.py	initial commit	2026-10-20 12:09:42 +08:00
rotary_embedding.py	initial commit	2026-10-20 12:09:42 +08:00
sampler_utils.py	initial commit	2026-10-20 12:09:42 +08:00
sampler.py	initial commit	2026-10-20 12:09:42 +08:00
vocab_parallel_embedding.py	Neuron: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +08:00