[Frontend] Advertise --enable-x/--disable-x for boolean CLI flags (#61479)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Misha Goin
2026-10-15 01:08:02 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 48f17b77bb
commit 1c4c319792
13 changed files with 118 additions and 36 deletions
@@ -39,7 +39,7 @@ Encoder engines should be launched with the following flags:
- `--enforce-eager` **(required)** – The current EPD implementation is only compatible with encoder instances running in this mode.
- `--no-enable-prefix-caching` **(required)** – Encoder instances do not consume KV cache; prefix caching is disabled to avoid conflicts with other features.
- `--disable-prefix-caching` **(required)** – Encoder instances do not consume KV cache; prefix caching is disabled to avoid conflicts with other features.
- `--max-num-batched-tokens=<large value>` **(default: 2048)** – This flag controls the token scheduling budget per decoding step and is irrelevant to encoder-only instances. **Set it to a very high value (effectively unlimited) to bypass scheduler limitations.** The actual token budget is managed by the encoder cache manager.
@@ -115,7 +115,7 @@ env "$DEVICE_AFFINITY_ENV=$GPU_E" vllm serve "$MODEL" \
--port "$ENCODE_PORT" \
--enforce-eager \
--enable-request-id-headers \
--no-enable-prefix-caching \
--disable-prefix-caching \
--max-num-batched-tokens 114688 \
--max-num-seqs "$MAX_NUM_SEQS" \
--allowed-local-media-path "${GIT_ROOT}"/tests/v1/ec_connector/integration \
@@ -108,7 +108,7 @@ env "$DEVICE_AFFINITY_ENV=$GPU_E" vllm serve "$MODEL" \
--port "$ENCODE_PORT" \
--enforce-eager \
--enable-request-id-headers \
--no-enable-prefix-caching \
--disable-prefix-caching \
--max-num-batched-tokens 114688 \
--max-num-seqs "$MAX_NUM_SEQS" \
--allowed-local-media-path "${GIT_ROOT}"/tests/v1/ec_connector/integration \