Search results

Use standard Hugging Face environment variables.

Status: Open.

#210 In AI-Hypercomputer/jetstream-pytorch;

· arueth opened on Jun 4, 2025

[Feature Request] Per request sampling params

Status: Open.

#185 In AI-Hypercomputer/jetstream-pytorch;

· qihqi opened on Sep 24, 2024

Make sure the server does not crash if the input is too long

Status: Open.

#183 In AI-Hypercomputer/jetstream-pytorch;

· qihqi opened on Sep 11, 2024

[RFC] Formalizing commandline arguments.

Status: Open.

#182 In AI-Hypercomputer/jetstream-pytorch;

· qihqi opened on Sep 10, 2024

Issues with prefill & generate

Status: Open.

#173 In AI-Hypercomputer/jetstream-pytorch;

· qihqi opened on Aug 21, 2024

Error Running <code>run_ray_serve_interleave</code> with Llama3 8B

Status: Open.

#169 In AI-Hypercomputer/jetstream-pytorch;

· ryanaoleary opened on Aug 7, 2024

Empty response returned for prompt responses when using run_server_with_ray.py and batch_size &gt; 1

Status: Open.

#137 In AI-Hypercomputer/jetstream-pytorch;

· richardsliu opened on Jun 27, 2024

Checkpoint conversion script breaks for meta-llama/llama-2-7b on HF

Status: Open.

#135 In AI-Hypercomputer/jetstream-pytorch;

· vivianrwu opened on Jun 24, 2024

Return Tuple(interleaveEngList, prefillEngineList, decodeEngineList) in create ray engine

Status: Open.

#107 In AI-Hypercomputer/jetstream-pytorch;

· FanhaiLu1 opened on May 29, 2024

Add regression test to detect service broken and performance degradation

Status: Open.

#94 In AI-Hypercomputer/jetstream-pytorch;

· FanhaiLu1 opened on May 21, 2024