Official Inference Code of EAGLE-4
docs: name the published 0.1.1 images in the release notes
Seyfal Sultanovea02a3bdf29a
diff --git a/docs/release-notes/0.1.1.md b/docs/release-notes/0.1.1.mdindex ea835ed..836a8f6 100644--- a/docs/release-notes/0.1.1.md+++ b/docs/release-notes/0.1.1.md@@ -22,7 +22,9 @@ environment, run your engine's install command with the pins below, then `eagle-| vLLM | `eagle-harness[vllm]==0.1.1`, `vllm==0.32.0rc1.dev283+eagle.4` (unchanged) || TokenSpeed | `eagle-harness[tokenspeed]==0.1.1`, `tokenspeed==0.1.1+eagle.5`, `tokenspeed-kernel==0.1.4+eagle.5`, `tokenspeed-scheduler==0.1.40+eagle.4` |-The published `0.1.0` images keep working with the commands in the engine guides. Images with 0.1.1 follow.+The images `ghcr.io/eagle-hq/eagle-4-sglang:0.1.1`, `ghcr.io/eagle-hq/eagle-4-vllm:0.1.1` and+`ghcr.io/eagle-hq/eagle-4-tokenspeed:0.1.1` carry these engines with `eagle-harness` 0.1.1. The+[install guide](../install.md#docker-images) lists them.**Breaking:** the configuration is streamlined. A config that still sets `"mode": "eval"`, `ragged`(`enabled`, `force_uniform`), `cost_model.ragged_draft_relax`, `cost_model.ragged_verify_threshold` or@@ -108,7 +110,8 @@ command of the [SGLang guide](../quickstart-sglang.md) and the vLLM rows the tun- SGLang above concurrency 64 is slower with speculation than without at a running cap of 512 (0.74× at 256,0.61× at 512); serve those loads without speculation for now.-- The `:0.1.0` images keep the 0.1.0 engines and `eagle-harness` 0.1.0; images with 0.1.1 follow.+- The `:0.1.1` images (`eagle-4-sglang`, `eagle-4-vllm`, `eagle-4-tokenspeed`) are CUDA only. There is no+ SGLang ROCm image: [build it](../install.md#build-the-rocm-image) yourself.- The SGLang ROCm install keeps `sglang==0.5.23.dev252+eagle.4.rocm` and, through its hash lock,`eagle-harness` 0.1.0 until the lock moves to the published 0.1.1 wheel.- [Known limits](../known-limits.md) lists the rest, and the [support matrix](../support-matrix.md) has every