yangzhuxinyzx fc3901beb4 [Core] Share SM70 AWQ and FP8 MoE stages and capture engine policy ...

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

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

..

basic_correctness

…

benchmarks

[Bench] Preserve teacher histories across chained comparisons

2026-10-06 02:40:47 +08:00

compile

[Core] Share DFlash attention and norm boundaries across TP sizes (#1025)

2026-10-07 15:10:21 +08:00

config

[Attention] Admit single-request DFlash split windows on 832-token pages

2026-10-07 02:08:52 +08:00

cuda

…

detokenizer

…

distributed

[Kernel] Enable qualified full-vocabulary Flash-Next MTP4 defaults (#821)

2026-10-05 19:59:24 +08:00

engine

…

entrypoints

…

evals

…

image

…

ir

…

kernels

[Test] Expect the documented index error from native PLE rows

2026-10-09 08:48:32 +08:00

lora

…

model_executor

[Core] Share DFlash attention and norm boundaries across TP sizes (#1025)

2026-10-07 15:10:21 +08:00

models

[Model] Integrate current main before GLM MTP configuration checks

2026-10-09 08:59:55 +08:00

multimodal

…

parser

…

platforms

…

plugins

…

plugins_tests

…

prompts

…

quantization

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

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

reasoning

…

renderers

…

rocm/aiter

…

samplers

…

spec_decode

…

standalone_tests

…

system_messages

…

tokenizers_

…

tool_parsers

…

tool_use

…

tools

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

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

tracing

…

transformers_utils

…

utils_

…

v1

Merge commit 'refs/codex-cleanup/main' into codex/macos-gloo-loopback-20261009

2026-10-09 10:07:15 +08:00

video

…

vllm_flash_attn

…

vllm_test_utils

…

weight_loading

…

__init__.py

…

ci_envs.py

…

conftest.py

…

test_access_log_filter.py

…

test_attention_backend_registry.py

…

test_config.py

…

test_embedded_commit.py

…

test_envs.py

…

test_fxgraphcache_pickle_patch.py

…

test_inputs.py

…

test_jit_monitor.py

…

test_logger.py

…

test_logprobs.py

…

test_outputs.py

…

test_pooling_params.py

…

test_ray_env_utils.py

…

test_ray_env.py

…

test_regression.py

…

test_scalartype.py

…

test_seed_behavior.py

…

test_sequence.py

…

test_sm70_gguf_teacher.py

[Bench] Capture conditioned full logits from the MTP target graph

2026-10-05 17:53:12 +08:00

test_sm70_graph_observer.py

[Test] Check named input phase RPC and capability enforcement

2026-10-05 12:32:54 +08:00

test_triton_utils.py

…

test_version.py

…

test_vllm_port.py

…

test_zen_cpu_platform_detection.py

…

utils.py

…