yangzhuxinyzxandOpenAI Codex fc88f450f7 [Test] Report prefill stalls within the measured online phase ...

Retain full crossing gaps separately and support deliberate prefix-reuse probes. Correct snapshot scalar argument positions for shared and separate NVFP4 dispatch.

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

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

..

sm70_awq_routes.json

…

sm70_fp8_routes.json

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

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

sm70_nvfp4_routes.json

[Test] Report prefill stalls within the measured online phase

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