yangzhuxinyzxandOpenAI Codex 19a2d4e99e [Core] Isolate prepared layer providers and shared draft weights ...

Co-authored-by: OpenAI Codex <noreply@openai.com>
Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-10 00:05:05 +08:00

..

data

[Test] Report prefill stalls within the measured online phase

2026-10-04 01:13:53 +08:00

fixtures

[Core] Share FP4 MoE stages and capture format policy

2026-10-09 11:50:23 +08:00

__init__.py

…

fp_quant.py

…

reference_mxfp4.py

…

test_auto_gptq.py

…

test_auto_round.py

…

test_awq_qpn_sm70.py

[Core] Share FP4 MoE stages and capture format policy

2026-10-09 11:50:23 +08:00

test_awq_sm70_fallback.py

…

test_awq_sm70_persistent_cap.py

…

test_awq_sm70_sorted_output_contract.py

…

test_blackwell_moe.py

…

test_block_fp8_qpn8_capabilities.py

[Kernel] Retain TurboMind for unsupported block QPN8 prefill rows

2026-10-03 08:28:15 +08:00

test_compressed_tensors.py

…

test_configs.py

…

test_cpu_offload.py

…

test_cpu_wna16.py

…

test_cutlass_w4a16.py

…

test_experts_int8.py

…

test_fp8_marlin_bmm_dequant.py

[Kernel] Retain TurboMind for unsupported block QPN8 prefill rows

2026-10-03 08:28:15 +08:00

test_fp8.py

…

test_gfx950_moe.py

…

test_gptq_dynamic.py

…

test_gptq_v2.py

…

test_lm_head.py

…

test_mixed_precision.py

…

test_modelopt.py

…

test_nvfp4_mxfp4_gating.py

…

test_online.py

…

test_per_token_kv_cache.py

…

test_quantization_config_args.py

…

test_quark_w4a16.py

…

test_quark.py

…

test_register_quantization_config.py

…

test_sm70_awq_active_grouped_decode.py

…

test_sm70_awq_compact_metadata.py

…

test_sm70_awq_indexed_prefill.py

…

test_sm70_awq_kernel_selection.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_awq_prefill_exact_dense.py

…

test_sm70_batched_gemm_layouts.py

[Core] Resolve runtime policy per engine at ordered defaults

2026-10-09 22:42:41 +08:00

test_sm70_channel_fp8_layout_guard.py

…

test_sm70_compressed_tensors_fastpaths.py

…

test_sm70_ct_fp8_cache_workspace.py

…

test_sm70_engine_workspaces.py

[Core] Bind native policy tokens without list conversion

2026-10-09 14:55:01 +08:00

test_sm70_fp4_mainflow.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_fp8_kernel_selection.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_fp8_prefill_exact_dense.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_fp8_workspace_aot_reload.py

[Core] Move SM70 serialized FP8 dispatch into the linear kernel lifecycle

2026-10-03 03:36:20 +08:00

test_sm70_fp32_lm_head_admission.py

[Core] Isolate prepared layer providers and shared draft weights

2026-10-10 00:05:05 +08:00

test_sm70_glm53_modelopt_nvfp4.py

…

test_sm70_local_workspace_capacity.py

…

test_sm70_modelopt_mixed_nvfp4.py

[Test] Repair twelve SM70 test cases broken by recent main changes

2026-10-09 08:39:54 +08:00

test_sm70_modelopt_nvfp4_kernel_oracle.py

…

test_sm70_modelopt_nvfp4.py

…

test_sm70_moe_backend_override.py

…

test_sm70_moe_buffers.py

[Core] Share SM70 AWQ and FP8 MoE stages and capture engine policy

2026-10-09 10:54:32 +08:00

test_sm70_moe_load_cache_release.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_moe_mainflow.py

[Core] Trim repeated tensor views and MoE host bookkeeping

2026-10-09 15:49:46 +08:00

test_sm70_mxfp4_moe.py

[Core] Share FP4 MoE stages and capture format policy

2026-10-09 11:50:23 +08:00

test_sm70_native_cache.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm70_native_policy.py

[Core] Resolve MoE native stages and close Phase B operator validation

2026-10-09 16:01:01 +08:00

test_sm70_nvfp4_grouped_decode_dispatch.py

[Kernel] Enable qualified Flash-Next batch defaults and MTP admission

2026-10-03 05:32:36 +08:00

test_sm70_nvfp4_integration.py

[Core] Share FP4 MoE stages and capture format policy

2026-10-09 11:50:23 +08:00

test_sm70_nvfp4_kernel_selection.py

…

test_sm70_nvfp4_qpn2.py

[Kernel] Enable measured dense NVFP4 small-prefill dispatch

2026-10-04 00:17:07 +08:00

test_sm70_online_qpn8.py

…

test_sm70_platform_gate_per_device.py

…

test_sm70_prepared_linear.py

[Core] Trim repeated tensor views and MoE host bookkeeping

2026-10-09 15:49:46 +08:00

test_sm70_quantized_model_compat.py

…

test_sm70_turbomind_adapter.py

…

test_sm70_turbomind_turing_gates.py

[Feature][SM75] Run ModelOpt NVFP4 and FP8 linears on Turing through the SM70 QPN kernels

2026-10-03 06:39:47 +08:00

test_sm70_warmup.py

[Core] Consolidate prepared SM70 linear and native policy ownership

2026-10-09 13:31:46 +08:00

test_sm72_volta_admission.py

[Build] Support SM72 targets and robust device diagnostics

2026-10-03 06:27:04 +08:00

test_torchao.py

…

test_trtllm_nvfp4_hidden_dim_padding.py

…

test_turboquant.py

…

test_turing_qpn_kernel_selection.py

[Bugfix] Preserve ModelOpt FP8 layout and fallback metadata

2026-10-03 06:46:36 +08:00

utils.py

…