@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / b2d9be6f7d
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 15, 06:00 UTC

[Docs] Remove WIP features in V1 guide (#19498)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Woosuk Kwon committed Jun 11, 2025 at 09:15 UTC b2d9be6f7d9249ce857d005aaef40b6ffe5b4414
1 file changed +1 -9
docs/usage/v1_guide.md
+1 -9
@@ -103,7 +103,7 @@ For a complete list of supported models, see the [list of supported models](http
103 | **LoRA** | <nobr>🚀 Optimized</nobr> |
104 | **Logprobs Calculation** | <nobr>🟢 Functional</nobr> |
105 | **FP8 KV Cache** | <nobr>🟢 Functional on Hopper devices ([PR #15191](https://github.com/vllm-project/vllm/pull/15191))</nobr>|
106 -| **Spec Decode** | <nobr>🚧 WIP ([PR #13933](https://github.com/vllm-project/vllm/pull/13933))</nobr>|
106 +| **Spec Decode** | <nobr>🚀 Optimized</nobr> |
107 | **Prompt Logprobs with Prefix Caching** | <nobr>🟡 Planned ([RFC #13414](https://github.com/vllm-project/vllm/issues/13414))</nobr>|
108 | **Structured Output Alternative Backends** | <nobr>🟢 Functional</nobr> |
109 | **Request-level Structured Output Backend** | <nobr>🔴 Deprecated</nobr> |
@@ -137,14 +137,6 @@ Support for logprobs with post-sampling adjustments is in progress and will be a
137
138 Currently prompt logprobs are only supported when prefix caching is turned off via `--no-enable-prefix-caching`. In a future release, prompt logprobs will be compatible with prefix caching, but a recomputation will be triggered to recover the full prompt logprobs even upon a prefix cache hit. See details in [RFC #13414](https://github.com/vllm-project/vllm/issues/13414).
139
140 -#### WIP Features
141 -
142 -These features are already supported in vLLM V1, but their optimization is still
143 -in progress.
144 -
145 -- **Spec Decode**: Currently, only ngram-based spec decode is supported in V1. There
146 - will be follow-up work to support other types of spec decode (e.g., see [PR #13933](https://github.com/vllm-project/vllm/pull/13933)). We will prioritize the support for Eagle, MTP compared to draft model based spec decode.
147 -
140 #### Deprecated Features
141
142 As part of the major architectural rework in vLLM V1, several legacy features have been deprecated.