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 4, 01:15 UTC
[Docs] Fix RLHF example links (#42073)
Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>
Ethan Feng committed
May 9, 2026 at 10:03 UTC
236bf9d152136f3f199f5bc23d283551c8604576
3 files changed
+6
-6
docs/training/async_rl.md
+1
-1
@@ -60,4 +60,4 @@ The key insight is that requests paused with `mode="keep"` will produce tokens f
60
61
## Example
62
63
-The [async RLHF example](../examples/rl/rlhf_async_new_apis.md) demonstrates this pattern with `vllm.AsyncLLMEngine`, NCCL weight transfer, and mid-flight pause/resume with validation.
63
+The [async RLHF example](../../examples/rl/rlhf_async_new_apis.py) demonstrates this pattern with `vllm.AsyncLLMEngine`, NCCL weight transfer, and mid-flight pause/resume with validation.
docs/training/weight_transfer/ipc.md
+2
-2
@@ -83,5 +83,5 @@ See [`IPCTrainerSendWeightsArgs`](https://github.com/vllm-project/vllm/blob/main
83
84
## Examples
85
86
-- [RLHF with IPC weight syncing (offline, Ray)](../../examples/rl/rlhf_ipc.md) - Colocated training and inference on a single GPU using Ray placement groups and CUDA IPC handles
87
-- [RLHF with IPC weight syncing (online serving, HTTP)](../../examples/rl/rlhf_http_ipc.md) - Weight transfer with a vLLM HTTP server where both server and trainer share the same GPU
86
+- [RLHF with IPC weight syncing (offline, Ray)](../../../examples/rl/rlhf_ipc.py) - Colocated training and inference on a single GPU using Ray placement groups and CUDA IPC handles
87
+- [RLHF with IPC weight syncing (online serving, HTTP)](../../../examples/rl/rlhf_http_ipc.py) - Weight transfer with a vLLM HTTP server where both server and trainer share the same GPU
docs/training/weight_transfer/nccl.md
+3
-3
@@ -114,6 +114,6 @@ The `names`, `dtype_names`, and `shapes` lists describe each parameter. These mu
114
115
## Examples
116
117
-- [RLHF with NCCL weight syncing (offline, Ray)](../../examples/rl/rlhf_nccl.md) - Trainer on one GPU, 2x tensor-parallel vLLM engine on two others, with packed NCCL weight broadcast
118
-- [RLHF with async weight syncing (offline, Ray)](../../examples/rl/rlhf_async_new_apis.md) - Async generation with mid-flight pause, weight sync, resume, and validation against a fresh model
119
-- [RLHF with NCCL weight syncing (online serving, HTTP)](../../examples/rl/rlhf_http_nccl.md) - Weight transfer with a running vLLM HTTP server using HTTP control plane and NCCL data plane
117
+- [RLHF with NCCL weight syncing (offline, Ray)](../../../examples/rl/rlhf_nccl.py) - Trainer on one GPU, 2x tensor-parallel vLLM engine on two others, with packed NCCL weight broadcast
118
+- [RLHF with async weight syncing (offline, Ray)](../../../examples/rl/rlhf_async_new_apis.py) - Async generation with mid-flight pause, weight sync, resume, and validation against a fresh model
119
+- [RLHF with NCCL weight syncing (online serving, HTTP)](../../../examples/rl/rlhf_http_nccl.py) - Weight transfer with a running vLLM HTTP server using HTTP control plane and NCCL data plane