Zheng Liand瑀澈 27c447653d model: support Qwen3.5 (#18489) ...

Co-authored-by: 瑀澈 <yuche.lz@alibaba-inc.com>

2026-02-10 00:27:59 +08:00

..

all_reduce

[1/N] Optimize All Reduce - Benchmark different AR operations (#13797)

2026-01-26 22:44:13 +08:00

decoding_attention_triton

Fix benchmark import for should_use_tensor_core (#17232)

2026-01-16 17:48:36 -05:00

deepep

…

deepseek

…

elementwise

…

flashinfer_allreduce_fusion

…

fused_moe_triton

model: support Qwen3.5 (#18489)

2026-02-10 00:27:59 +08:00

quantization

Refactor tuning block wise kernel and opt Qwen/Qwen3-VL-32B-Instruct-FP8 (#14141)

2025-12-08 09:24:58 +08:00

scheduler_batch

…

sliding_window_attention_triton

…