mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-08-21 22:43:44 +00:00
e80614fc2d
Some checks failed
Book-CI / test (push) Waiting to run
Book-CI / test-1 (push) Waiting to run
Book-CI / test-2 (push) Waiting to run
Deploy / deploy (macos-latest) (push) Waiting to run
Deploy / deploy (ubuntu-latest) (push) Waiting to run
Deploy / deploy (windows-latest) (push) Waiting to run
Release Fake Tag / publish (push) Has been cancelled
Release to PyPI / Build & publish sglang-kt (push) Has been cancelled
Release to PyPI / Build kt-kernel (Python 3.11) (push) Has been cancelled
Release to PyPI / Build kt-kernel (Python 3.12) (push) Has been cancelled
Release to PyPI / Publish kt-kernel to PyPI (push) Has been cancelled
Release to PyPI / Build & publish ktransformers shell sdist (push) Has been cancelled
* feat(sft): support distributed activation reuse policies * feat(sft): add frozen-base INT8 LoRA training * fix(sft): make INT8 expert LoRA rank-zero authoritative * fix(sft): preserve DeepSeek router LoRA routing * feat(sft): enable persistent INT8 LoRA training * perf(sft): accelerate INT8 VNNI with oneDNN BRGEMM * perf(int8): fuse oneDNN compensation into backward repack * [feat]: support BF16 expert LoRA training * [fix]: honor forwarded activation policy in SFT workers * feat(sft): add native block-FP8 routed expert LoRA * feat(sft): expose explicit expert placeholder ownership * fix(sft): publish fused adapter artifacts atomically * feat(sft): own artifact and adapter lifecycle contracts * fix(sft): harden artifact and rank-local contracts * fix(sft): auto-adapt owner before adapter restore * style(sft): keep lifecycle comments concise * fix(sft): require fused adapter manifests * test(sft): use spawn for distributed workers * fix(sft): preserve runtime checkpoint metadata * fix(sft): validate wrapped runtime configuration * fix(sft): preserve expert format provenance * fix(sft): own routed experts during device dispatch * test(sft): lock explicit quantization conflict * fix(cpu): make shared memory buffers lifetime-safe * release: prepare v0.7.0 |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_amd_placeholder.py | ||
| test_basic_cpu.py | ||
| test_convert_kt_to_sglang_adapter.py | ||
| test_convert_kt_to_sglang_adapter_integration.py | ||
| test_cpu_detect_metadata.py | ||
| test_cuda_placeholder.py | ||
| test_load_experts_count_guard.py | ||
| test_moe_amx_accuracy_int4.py | ||
| test_moe_amx_accuracy_int4_1.py | ||
| test_moe_amx_accuracy_int4_1k.py | ||
| test_moe_amx_accuracy_int8.py | ||
| test_moe_amx_bench_int4.py | ||
| test_moe_amx_bench_int4_1.py | ||
| test_moe_amx_bench_int4_1k.py | ||
| test_moe_amx_bench_int8.py | ||
| test_moe_avx2_accuracy_bf16.py | ||
| test_moe_avx2_accuracy_fp8.py | ||
| test_moe_gptq_int4_accuracy.py | ||
| test_moe_rawint4_accuracy.py | ||
| test_moe_rawint4_load_equivalence.py | ||
| test_port_checker.py | ||
| test_sft_activation_policy.py | ||
| test_sft_artifact_contracts.py | ||
| test_sft_authoritative_grad.py | ||
| test_sft_backend_dispatch.py | ||
| test_sft_checkpoint_reuse.py | ||
| test_sft_conv3d_compat.py | ||
| test_sft_ephemeral_int8.py | ||
| test_sft_force_fused_expert_lora.py | ||
| test_sft_fp8_load_entry.py | ||
| test_sft_fp8_loader.py | ||
| test_sft_full_checkpoint.py | ||
| test_sft_int8_numerical.py | ||
| test_sft_omp_threads.py | ||
| test_sft_persistent_int8_manifest.py | ||
| test_sft_profiler.py | ||
| test_sft_qwen3_vl_moe.py | ||
| test_sft_router_grad.py | ||
| test_sft_runtime_ownership.py | ||
| test_sft_shared_expert.py | ||