[Feature] Support block scheduler v1 for FD (#2928)

* Support FD block scheduler v1

* Support FD block scheduler v1

* Support FD block scheduler v1

* Fix according to copilot review

* Fix according to review

* Remove is_dummy

* Fix bug when real_bsz=1

* Fix infer first token cost time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
chenjian
2025-07-23 20:31:31 +08:00
committed by GitHub
parent ca0f71bd39
commit 85a78d695d
16 changed files with 898 additions and 40 deletions

View File

@@ -76,6 +76,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
"EXPORTER_OTLP_ENDPOINT": lambda: os.getenv("EXPORTER_OTLP_ENDPOINT"),
# set traec exporter_otlp_headers.
"EXPORTER_OTLP_HEADERS": lambda: os.getenv("EXPORTER_OTLP_HEADERS"),
# enable kv cache block scheduler v1 (no need for kv_cache_ratio)
"ENABLE_V1_KVCACHE_SCHEDULER": lambda: int(os.getenv("ENABLE_V1_KVCACHE_SCHEDULER", "0")),
}