yangzhuxinyzxandOpenAI Codex e1684f6d10 [CI/Build] Freeze merge gate baseline before scoped checks ...

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

2026-10-05 02:36:28 +08:00

..

ep_kernels

[Misc] Added curl retries in install_python_libraries.sh (#36700)

2026-04-24 01:19:30 +00:00

minimax_h3

[Test] Record H3 residual sharding and 58.79-second development evidence

2026-09-08 23:02:24 +08:00

pre_commit

[Core] Resolve SM70 DFlash2 verifier policy per engine

2026-10-03 07:41:12 +08:00

profiler

…

qwen4_exp

[Model][SM70] Require calibrated E4M3 MTP draft scales

2026-10-03 13:20:18 +08:00

torch_patches

[Build][SM70] Ship the torch 2.10.0 backport that lets a fresh process load bundled AOT artifacts

2026-10-02 19:09:59 +08:00

vllm-rocm

[ROCm] [Release] Update ROCm variant from rocm700 to rocm721 (#38413)

2026-03-28 06:07:03 +00:00

vllm-tpu

Disable build isolation to bypass CUDA related deps for vllm-tpu (#43038)

2026-05-21 18:00:52 -04:00

build_deepgemm_C.py

[Build] DeepGEMM: trim comments, add integration notes + TODOs (#42429)

2026-05-12 15:57:58 -07:00

check_repo.sh

…

check_sm70_release_artifact.py

[Release] Make SM70 wheel delivery self-contained

2026-09-30 00:06:51 +08:00

check_wheel_deepgemm.py

[Build] Build bundled DeepGEMM _C per-Python so the wheel imports on every CPython (#41516)

2026-05-12 10:27:29 -04:00

flashinfer-build.sh

[NVIDIA] Add sm_110 (Jetson Thor) to CUDA 13.0 build targets (#39233)

2026-04-23 15:42:14 -04:00

generate_cmake_presets.py

Add structure to requirements/ directory (#39024)

2026-04-10 13:46:41 -07:00

generate_env_reference.py

[Core] Reduce the public SM70 environment control surface

2026-10-03 05:55:06 +08:00

generate_versions_json.py

…

install_deepgemm.sh

[Feat] DeepSeek V4 Rebased (#40860)

2026-04-26 18:31:08 -07:00

install_gdrcopy.sh

…

install_nixl_from_source_ubuntu.py

…

install_protoc.sh

[CI] Pin protoc binary in rust-build stages (#43292)

2026-05-21 03:38:07 -07:00

install_torchcodec_rocm.sh

…

merge_gate.sh

[CI/Build] Freeze merge gate baseline before scoped checks

2026-10-05 02:36:28 +08:00

prepare-flashinfer-sm70.sh

[Core] Sync SM70 performance stack

2026-07-15 23:35:54 +08:00

qwen38_flash_next_nvfp4_smoke.py

[Core][SM70] Repair Qwen4Exp PLE and AMD integration

2026-08-28 11:53:21 +08:00

report_build_time_ninja.py

…

run_cpu_tests.py

[CI/Build] Add scoped CPU and SM70 profile merge checks

2026-10-02 20:36:15 +08:00

setup_deepgemm_pythons.sh

[CI/Build] Fix ShellCheck findings

2026-08-01 17:09:26 +08:00

sm70_awq_route_snapshot.py

[Test] Make AWQ selector probes independent of the host platform

2026-10-03 02:01:54 +08:00

sm70_dflash2_route_snapshot.py

[Core] Retire failed DFlash2 candidate-order override

2026-10-03 08:09:52 +08:00

sm70_flash_next_route_snapshot.py

[Core] Scope gated norm defaults to each qualified Flash-Next engine

2026-10-03 07:43:51 +08:00

sm70_fp8_policy_snapshot.py

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

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

sm70_fp8_route_snapshot.py

[Core] Resolve SM70 DFlash2 verifier policy per engine

2026-10-03 07:41:12 +08:00

sm70_route_snapshot.py

[Test] Report prefill stalls within the measured online phase

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