Official Inference Code of EAGLE-4
docs: name the 0.1.2 images
Seyfal Sultanovdaeb41ecd2fc
diff --git a/README.md b/README.mdindex 205a979..51c9d2c 100644--- a/README.md+++ b/README.md@@ -76,7 +76,7 @@ Start an SGLang server with Docker:```bashdocker run --gpus all --ipc host -p 127.0.0.1:30000:30000 \-e HF_HOME=/hf -v ~/.cache/huggingface:/hf \- ghcr.io/eagle-hq/eagle-4-sglang:0.1.1 \+ ghcr.io/eagle-hq/eagle-4-sglang:0.1.2 \sglang serve --model-path Qwen/Qwen3.8-27B --host 0.0.0.0 \--disable-overlap-schedule --speculative-algorithm EAGLE_HARNESS \--speculative-draft-model-path EAGLE-Corp/Qwen3.8-27B-EAGLE4 \diff --git a/docs/install.md b/docs/install.mdindex b832f37..e59674b 100644--- a/docs/install.md+++ b/docs/install.md@@ -74,14 +74,14 @@ wheel hash for the SGLang image build.## Docker images-Each image has one patched engine and `eagle-harness` 0.1.1 installed. The engine guides show the `docker run`+Each image has one patched engine and `eagle-harness` 0.1.2 installed. The engine guides show the `docker run`command for each one.| Engine | Image || --- | --- |-| SGLang CUDA | `ghcr.io/eagle-hq/eagle-4-sglang:0.1.1` |-| vLLM CUDA | `ghcr.io/eagle-hq/eagle-4-vllm:0.1.1` |-| TokenSpeed CUDA | `ghcr.io/eagle-hq/eagle-4-tokenspeed:0.1.1` |+| SGLang CUDA | `ghcr.io/eagle-hq/eagle-4-sglang:0.1.2` |+| vLLM CUDA | `ghcr.io/eagle-hq/eagle-4-vllm:0.1.2` |+| TokenSpeed CUDA | `ghcr.io/eagle-hq/eagle-4-tokenspeed:0.1.2` || SGLang ROCm | not published, [build it](#build-the-rocm-image) |To run a newer `eagle-harness` in an image, run `pip install -U eagle-harness` inside the container.diff --git a/docs/quickstart-sglang.md b/docs/quickstart-sglang.mdindex 69daed9..ee61628 100644--- a/docs/quickstart-sglang.md+++ b/docs/quickstart-sglang.md@@ -25,7 +25,7 @@ Or run the published image, which has the engine and EAGLE-4 installed:```bashdocker run --gpus all --ipc host -p 127.0.0.1:30000:30000 \-e HF_HOME=/hf -v ~/.cache/huggingface:/hf \- ghcr.io/eagle-hq/eagle-4-sglang:0.1.1 \+ ghcr.io/eagle-hq/eagle-4-sglang:0.1.2 \sglang serve --model-path Qwen/Qwen3.8-27B --host 0.0.0.0 \--disable-overlap-schedule --speculative-algorithm EAGLE_HARNESS \--speculative-draft-model-path EAGLE-Corp/Qwen3.8-27B-EAGLE4 \diff --git a/docs/quickstart-vllm.md b/docs/quickstart-vllm.mdindex 8cceb16..3240db2 100644--- a/docs/quickstart-vllm.md+++ b/docs/quickstart-vllm.md@@ -26,7 +26,7 @@ Or run the published image, which has the engine and EAGLE-4 installed and start```bashdocker run --gpus all --ipc host -p 127.0.0.1:8000:8000 \-e HF_HOME=/hf -v ~/.cache/huggingface:/hf -e VLLM_USE_V2_MODEL_RUNNER=1 \- ghcr.io/eagle-hq/eagle-4-vllm:0.1.1 \+ ghcr.io/eagle-hq/eagle-4-vllm:0.1.2 \Qwen/Qwen3.8-27B \--attention-backend CUSTOM --linear-backend flashinfer_cutedsl \--speculative-config '{"method": "eagle_harness", "model": "EAGLE-Corp/Qwen3.8-27B-EAGLE4", "method_config": {"mode": "static", "node_top_k": 4, "tree_depth": 14, "max_verify_width": 16}}'diff --git a/docs/release-notes/0.1.2.md b/docs/release-notes/0.1.2.mdindex ca915d9..15e58d7 100644--- a/docs/release-notes/0.1.2.md+++ b/docs/release-notes/0.1.2.md@@ -23,8 +23,8 @@ environment, run your engine's install command with the pins below, then `eagle-| vLLM | `eagle-harness[vllm]==0.1.2`, `vllm==0.32.0rc1.dev283+eagle.4` (unchanged) || TokenSpeed | `eagle-harness[tokenspeed]==0.1.2`, `tokenspeed==0.1.1+eagle.5`, `tokenspeed-kernel==0.1.4+eagle.5`, `tokenspeed-scheduler==0.1.40+eagle.4` (unchanged) |-The `:0.1.1` images carry `eagle-harness` 0.1.1. The [install guide](../install.md#docker-images) lists the current-images. Nothing in the configuration changes: every 0.1.1 configuration loads as before.+The `:0.1.2` images carry `eagle-harness` 0.1.2 on the same engines. The [install guide](../install.md#docker-images)+lists them. Nothing in the configuration changes: every 0.1.1 configuration loads as before.## What changeddiff --git a/docs/release.env b/docs/release.envindex 722d650..b2db9aa 100644--- a/docs/release.env+++ b/docs/release.env@@ -5,7 +5,7 @@# Engine wheel assets and image tags have their own release versions.# Advance their pins only after the corresponding artifacts pass release qualification.export EAGLE_HARNESS_VERSION='0.1.2' # x-release-please-version-export EAGLE_IMAGE_VERSION='0.1.1'+export EAGLE_IMAGE_VERSION='0.1.2'export EAGLE_WHEEL_ROOT='https://eagle-hq.github.io/EAGLE-4/whl'export EAGLE_CUDA_INDEX="$EAGLE_WHEEL_ROOT/cu130/"export EAGLE_ROCM_INDEX="$EAGLE_WHEEL_ROOT/rocm/"