Repository navigation
[vLLM-TorchTPU] Add DeepSeek-V4-Flash and DeepSeek-V4-Pro Ironwood recipes - #384
Merged
anthonsu merged 1 commit intoNov 4, 2026
Conversation
There was a problem hiding this comment.
Code Review
This pull request introduces deployment guides and Kubernetes manifests for serving DeepSeek-V4-Flash and DeepSeek-V4-Pro models using vLLM with the TorchTPU backend on GKE with Ironwood TPUs. The feedback highlights critical startup issues due to invalid CLI arguments like --no-enable-prefix-caching and --generation-config in the server manifests. Additionally, it is recommended to replace the tcpSocket readiness probes with httpGet probes on the /health endpoint to ensure traffic is not routed to the pods before the models are fully loaded and compiled.
inucool12
marked this pull request as ready for review
November 3, 2026 22:21
anthonsu
approved these changes
Nov 4, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add GKE serving and benchmark recipes for DeepSeek-V4-Flash and DeepSeek-V4-Pro using the vLLM TorchTPU backend (
vllm/vllm-torchtpu:v0.29.0) on Ironwood (TPU v7x):inference/ironwood/vLLM/vLLM-TorchTPU/DeepSeek-V4-Flash:Deploymentontpu7x-standard-4t(2x2x1topology, 4 chips / 8 TensorCores).TP=1, DP=8, EP=8,deepseek_v4_fp8quantization with load-time FP4 MoE weight requantization (W4A8), andfp8_e4m3KV cache.8192input /1024output,2048prompts) serving benchmark configuration and sample results.inference/ironwood/vLLM/vLLM-TorchTPU/DeepSeek-V4-Pro:LeaderWorkerSet+ Ray deployment across 2×tpu7x-standard-4t(2x2x2topology, 8 chips / 16 TensorCores).TP=1, DP=16, EP=16(--enable-ep-weight-filter,--safetensors-load-strategy=prefetch),deepseek_v4_fp8quantization with fused EP MoE v2 W4A8 (USE_MOE_FUSED_EP_KERNEL=1,MOE_FUSED_EP_ENABLE_W4A8=1), andfp8_e4m3KV cache.8192input /1024output,2048prompts,max-concurrency=1024) serving benchmark configuration.