Skip to content

Commit d499a34

Browse files
committed
update readme
Signed-off-by: Maya Barnea <mayab@il.ibm.com>
1 parent e8049e7 commit d499a34

2 files changed

Lines changed: 3 additions & 3 deletions

File tree

DEVELOPMENT.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -448,7 +448,7 @@ The `deploy/components/` directory contains all reusable Kustomize components:
448448
- `vllm-decode/` — Decode pod with routing sidecar
449449

450450
**Deployment overlays** — applied on top of the base components:
451-
- `overlays/simulator/` — adds `--mode=${VLLM_SIM_MODE}`, vllm renderer sidecar, KV cache args, and `--zmq-endpoint` on Decode. Included by default in all dev scenario overlays.
451+
- `overlays/simulator/` — adds `--mode=${VLLM_SIM_MODE}`, KV cache args, and `--zmq-endpoint` on Decode. Included by default in all dev scenario overlays.
452452
- `overlays/real-vllm/` — adds `--kv-events-config` on Decode, `--ec-transfer-config` on Encode, and a shared PVC for encoder embeddings.
453453

454454
**Infrastructure components** — shared cluster infrastructure:
@@ -524,7 +524,7 @@ a shared PVC (`ec-cache-pvc`) for encoder embeddings transfer.
524524

525525
| Component | What it adds | When to use |
526526
|---|---|---|
527-
| `overlays/simulator/` | `--mode=${VLLM_SIM_MODE}`, vLLM renderer, KV cache args, `--zmq-endpoint` on Decode | Dev/test with simulator image |
527+
| `overlays/simulator/` | `--mode=${VLLM_SIM_MODE}`, KV cache args, `--zmq-endpoint` on Decode | Dev/test with simulator image |
528528
| `overlays/real-vllm/` | `--kv-events-config` on Decode (per-pod ZMQ publisher), `--ec-transfer-config` on Encode, ec-cache PVC | Production with real vLLM image |
529529

530530
| Variable | Default | Description |

deploy/environments/dev/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ scenario-specific patches. The atomic components live in `deploy/components/`:
99
| `vllm-decode/` | Decode pod — always deployed, includes routing sidecar (removed in EPD scenario) |
1010
| `vllm-prefill/` | Prefill pod — deployed when `DISAGG_P=true` |
1111
| `vllm-encode/` | Encoder pod — deployed when `DISAGG_E=true` |
12-
| `overlays/simulator/` | Adds `--mode=${VLLM_SIM_MODE}`, vLLM render, KV cache and ZMQ args (included by all scenario overlays) |
12+
| `overlays/simulator/` | Adds `--mode=${VLLM_SIM_MODE}`, KV cache and ZMQ args (included by all scenario overlays) |
1313

1414
These overlays are used by both `scripts/kind-dev-env.sh` (for local KIND clusters)
1515
and e2e tests (via `kustomize build` + env var substitution).

0 commit comments

Comments
 (0)