Mohammad Hijjawi 44fbb184d5 [fix](cli): fill in the model name and path in kt model remove/edit warnings (#2220)

2026-10-12 12:44:24 +08:00

..

__init__.py

add ci (#1642)

2025-11-25 20:52:08 +08:00

test_amd_placeholder.py

add ci (#1642)

2025-11-25 20:52:08 +08:00

test_basic_cpu.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_cli_model_remove.py

[fix](cli): fill in the model name and path in kt model remove/edit warnings (#2220)

2026-10-12 12:44:24 +08:00

test_convert_kt_to_sglang_adapter_integration.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_convert_kt_to_sglang_adapter.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_cpu_detect_metadata.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_cuda_placeholder.py

add ci (#1642)

2025-11-25 20:52:08 +08:00

test_deepseek_v4_cache.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_load_experts_count_guard.py

[fix(loader)]: correct off-by-one expert-count guard in load_experts (#2026)

2026-06-07 23:41:04 +08:00

test_moe_amx_accuracy_int4_1.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_accuracy_int4_1k.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_accuracy_int4.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_accuracy_int8.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_bench_int4_1.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_bench_int4_1k.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_bench_int4.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

test_moe_amx_bench_int8.py

[feat](kt-kernel): CPU-GPU experts sched (#1796)

2026-01-16 17:01:15 +08:00

test_moe_avx2_accuracy_bf16.py

[feat] : Add MACA backend support for kt-kernel and fix CPU MoE tests (#2044)

2026-06-16 16:49:06 +08:00

test_moe_avx2_accuracy_fp8.py

[feat] : Add MACA backend support for kt-kernel and fix CPU MoE tests (#2044)

2026-06-16 16:49:06 +08:00

test_moe_gptq_int4_accuracy.py

[feat](kt-kernel): packed-int4-resident AVX-VNNI-256 GPTQ INT4 backend (#2187)

2026-09-07 20:20:04 +08:00

test_moe_rawint4_accuracy.py

[perf]: add K2 RAWINT4 prefill mat-mat dispatch (#2080)

2026-07-19 21:43:01 +08:00

test_moe_rawint4_load_equivalence.py

[fix](kt-kernel): AVX-VNNI-256 RAWINT4 per-expert weight loading (#2092)

2026-07-19 17:24:52 +08:00

test_mxfp4_sft_api.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_mxfp4_sft_numerical.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_mxfp4_sft_reference.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_port_checker.py

[fix](cli): detect bound ports before launch (#2071)

2026-07-06 18:25:31 +08:00

test_sft_activation_policy.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_sft_artifact_contracts.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_authoritative_grad.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_sft_backend_dispatch.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_checkpoint_reuse.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_conv3d_compat.py

[feat](sft): support Qwen VLM MoE fine-tuning (#2156)

2026-08-17 10:51:55 +08:00

test_sft_ephemeral_int8.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_force_fused_expert_lora.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_fp8_load_entry.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_sft_fp8_loader.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_full_checkpoint.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_inference_lifetime.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00

test_sft_int8_numerical.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_omp_threads.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_persistent_int8_manifest.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_profiler.py

[feat](kt-kernel): end-to-end full-parameter and LoRA SFT(#2094)

2026-07-23 21:23:34 +08:00

test_sft_qwen3_vl_moe.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_router_grad.py

[feat] Add native RAWINT4 routed-expert LoRA SFT for Kimi K2.5/K2.6 (#2186)

2026-09-10 17:05:16 +08:00

test_sft_runtime_ownership.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

test_sft_shared_expert.py

feat(sft) Deepseek v4 flash LoRA (#2216)

2026-09-30 21:29:43 +08:00