Record · pytorch.org
Up to 580tps! New Speed Record of Qwen3.5-397B-A17B on GPU for Agentic Workloads with TokenSpeed
PyTorch Blog · 27 May 2026 · 18 min read
A post on pytorch.org, published 27 May 2026, has not been cited by any blog yet (corpus.blog, measured 12 October 2026).
A record is what was published and who pointed at it. The text of the post is not shown here: read it at the source, or at its Wayback capture.
0blogs citing
| Period | Blogs | Links |
|---|---|---|
| All time | 0 | 0 |
| Last 90 days | 0 | 0 |
| Last 30 days | 0 | 0 |
| Last 7 days | 0 | 0 |
| Words blogs link it with | 0 |
|---|---|
| External links | 5 |
| Length | 3,931 |
Cited by
No blog we hold has cited this post yet.
Links from this post
Link
Host
huggingface.co
lightseek.org
github.com
Elsewhere on pytorch.org (1)
Similar posts
6 Aug 2026
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72
NVIDIA Developer Blog
12 Aug 2026
LightSeek Foundation Releases TokenSpeed, an Open-Source LLM Inference Engine Targeting TensorRT-LLM-Level Performance for Agentic Workloads
marktechpost.com
7 May 2026
Alibaba Qwen Team Releases Qwen3.5-397B MoE Model with 17B Active Parameters and 1M Token Context for AI agents
marktechpost.com
16 Feb 2026
Deploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM
AWS Machine Learning
9 Sept 2026
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
NVIDIA Developer Blog
26 Aug 2026
MI355X versus GB300 NVL72 Inference Performance: 20x Gap on Qwen3.5 SGLang
inferencex.semianalysis.com
25 Aug 2026
Alibaba Qwen Team Releases Qwen 3.5 Medium Model Series: A Production Powerhouse Proving that Smaller AI Models are Smarter
marktechpost.com
24 Feb 2026
PD Serving of Qwen3.8-2.4T
vLLM Blog
21 Sept 2026
12 Aug 2026
Something wrong here? Report a problem