Zijie Tian 45efcf0db1 ✨ feat: add --dtype parameter to test_ruler.py ...

Support models with float32 default dtype (e.g., Nemotron).
FlashAttention requires fp16/bf16, so dtype must be specified.

Usage: --dtype bfloat16

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-28 13:56:15 +08:00

..

__init__.py

[WIP] NEED refactor nanovllm mechenism.

2025-12-22 23:52:56 +08:00

bench_estimate_block_size.py

📝 docs: add estimate block_size performance analysis

2026-01-28 06:24:28 +08:00

modeling_qwen3.py

[refactor] Refactor needle test.

2026-01-03 19:19:37 +08:00

test_chunk_attention_graph_reuse.py

📝 docs: add CUDA Graph optimization plan for offload mode decode

2026-01-22 02:12:24 +08:00

test_chunk_attention_graph.py

✨ feat: add chunk attention CUDA graph test for block sparse attention

2026-01-22 00:57:05 +08:00

test_cudagraph_memory.py

[test] Added test_cudagraph_memory.py.

2026-01-21 03:30:36 +08:00

test_hierarchical_estimate.py

✅ test: add hierarchical block sum estimation validation

2026-01-28 06:24:35 +08:00

test_needle_ref.py

[refactor] Refactor needle test.

2026-01-03 19:19:37 +08:00

test_needle.py

[WIP] Before integrate the xattn operator.

2026-01-19 21:19:21 +08:00

test_quest_policy.py

[WIP] move metadata to GPU.

2026-01-06 23:32:32 +08:00

test_ruler.py

✨ feat: add --dtype parameter to test_ruler.py

2026-01-28 13:56:15 +08:00

test_sequential.py

[WIP] Before fix bench_offload.py.

2026-01-06 18:41:08 +08:00

test_xattn_bsa.py

[WIP] Before refactor the compute)_chunked_prefill.

2026-01-23 03:36:12 +08:00

test_xattn_chunked.py

[WIP] Before refactor the compute)_chunked_prefill.

2026-01-23 03:36:12 +08:00

test_xattn_estimate_chunked.py

feat: add xattn_estimate_chunked for chunked prefill support

2026-01-22 01:13:17 +08:00

test_xattn_kernels.py

[WIP] Before refactor the compute)_chunked_prefill.

2026-01-23 03:36:12 +08:00

utils.py

[WIP] Before fix bench_offload.py.

2026-01-06 18:41:08 +08:00