Alex Cheema ccf4d91d55 add script to reproduce GPU lock issue ...

Repeatedly sends chat completions to Llama-3.2-1B-Instruct-4bit on a
single node and detects when a request stalls for >5s.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-24 09:44:07 -08:00

..

config_examples

Strip Claude headers to improve prefix cache hit rates (#1552)

2026-02-19 18:29:34 +00:00

prompt.txt

Consolidate!!! Fixes

2025-12-03 12:19:25 +00:00

quantize_and_upload.py

Ciaran/flux1 kontext (#1394)

2026-02-06 16:20:31 +00:00

reproduce_gpu_lock.py

add script to reproduce GPU lock issue

2026-02-24 09:44:07 -08:00

run_llm.py

8000 -> 52415 (#915)

2025-12-18 18:39:44 +00:00

run_llm.sh

8000 -> 52415 (#915)

2025-12-18 18:39:44 +00:00

set_rdma_network_config.sh

shfmt

2026-01-29 15:24:36 +00:00

test_trust_remote_code_attack.sh

Final fixes for release (#1603)

2026-02-23 21:10:15 +00:00