vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep (blog.vllm.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of blog.vllm.ai: vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep

First screen, captured 9 months ago.

Looks similar

Screenshot of x86.lol: The Polyglot NixOS

The Polyglot NixOS (x86.lol)

114 points by todsacerdoti 10 months ago | 39 comments

Screenshot of ziglang.org: Zig's new bitCast semantics and LLVM back end improvements

Zig's new bitCast semantics and LLVM back end improvements (ziglang.org)

266 points by kouosi 4 months ago | 135 comments

Screenshot of peter.eisentraut.org: PostgreSQL and FIPS Mode

PostgreSQL and FIPS Mode (peter.eisentraut.org)

65 points by chmaynard 2 years ago | 23 comments

Screenshot of vllora.dev: Debug Mode for LLMs in vLLora

Debug Mode for LLMs in vLLora (vllora.dev)

43 points by mrun1729 10 months ago | 4 comments

Screenshot of byroot.github.io: Optimizing Ruby's JSON, Part 1

Optimizing Ruby's JSON, Part 1 (byroot.github.io)

241 points by todsacerdoti 1 year ago | 56 comments

Screenshot of mwilczynski.dev: Igniting the GPU: From Kernel Plumbing to 3D Rendering on RISC-V

Igniting the GPU: From Kernel Plumbing to 3D Rendering on RISC-V (mwilczynski.dev)

90 points by michalwilczynsk 10 months ago | 8 comments