0 Fork 0

Files

T

ZhaochenggggandCopilot 5d216a8bbe [Bugfix][SM70] Honor explicit compilation settings in Flash-V100 policies

Fill mode and cudagraph_mode independently only when they are unset in
both SM70 Flash-V100 graph policies. Preserve explicit NONE, PIECEWISE,
STOCK_TORCH_COMPILE and the other enum values without disabling the
default baseline for unconfigured fields.

Report the resolved policy modes instead of hard-coded defaults. Add
75 CPU-only source-policy regression cases using the real policy body,
enums and environment readers with mocked hardware, and document the
precedence rule. No Torch, GPU or model download is required by these
isolated tests.

Related: #614 (configuration precedence only). This broader alternative
to #727 also covers non-NONE overrides and the no-compile decode policy;
it does not claim to fix the separate dynamic-shape inference crash.

Validation: 58 failures / 17 passes with the unchanged main policy,
75 passes after the fix; repository pre-commit hooks pass, including
Ruff, typos, mypy and documentation checks.

Signed-off-by: Zhaochengggg <87113558+zhaochengggg@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-02 20:45:01 +08:00

conserving_memory.md

…

engine_args.md

[Docs] Reorganize online serving docs. (#41907 )

2026-05-19 14:43:18 +08:00

env_vars.md

…

model_resolution.md

…

optimization.md

[Bugfix][SM70] Honor explicit compilation settings in Flash-V100 policies

2026-10-02 20:45:01 +08:00

README.md

…

serve_args.md

…

README.md

Configuration Options

This section lists the most common options for running vLLM.

There are three main levels of configuration, from highest priority to lowest priority: