3 people 6a4b81e2d9 Refactor(qwen3-vl) optimize position encoding interpolation (#16781) ...

Signed-off-by: chenzhenyang <andy271828@163.com>
Signed-off-by: chenzhenyang <chenzhenyang@moonshot.cn>
Co-authored-by: chenzhenyang <chenzhenyang@moonshot.cn>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>

2026-02-05 10:26:35 -08:00

..

ascend

[NPU] support GPTQ quantization on npu (#15203)

2026-01-29 15:48:18 +08:00

configs

…

cpu

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

models

Migrate 4-GPU/8-GPU workflow jobs to stage-c and add CI registry decorators (#17299)

2026-01-31 22:37:22 -08:00

xpu

[XPU] Integrate MoE and minor improvements in XPU attention backend (#13561)

2026-02-04 23:09:59 -08:00

double-sparsity-config-Llama-3.1-8B-Instruct.json

…

experiment_runner.py

…

kv_cache_scales_llama3_1_8b.json

Support FP8 E4M3 KV Cache (#2786)

2025-01-12 21:17:11 -08:00

kv_cache_scales_llama3_8b.json

support e4m3 kvcache in qwen2 & add kv scaling facotr json (#2894)

2025-01-18 11:43:22 +08:00

kv_cache_scales_qwen2_1_5b.json

…

parse_results.py

…

run_suite.py

[XPU] Integrate MoE and minor improvements in XPU attention backend (#13561)

2026-02-04 23:09:59 -08:00

test_embed_interpolate_unittest.py

Refactor(qwen3-vl) optimize position encoding interpolation (#16781)

2026-02-05 10:26:35 -08:00