George Hotz and GitHub
c2625c78cb
scalar ALU index fix + llm: preserve_thinking ( #17381 )
...
* cstyle: scalar ALU index fix, serve: preserve_thinking, test: fix Handler import
- cstyle.py: return scalar directly when ALU buffer has 1 element
- cli.py: add preserve_thinking param to FallbackTemplate.render
- serve.py: pass preserve_thinking=True when rendering chat completions
- test_llm_server.py: fix import to use Handler from llm.serve
* real fix
2026-08-03 15:10:21 -07:00
..
2026-02-03 13:52:36 +08:00
2026-06-03 16:21:24 -04:00
2026-04-13 16:54:39 -04:00
2026-06-29 17:41:31 -04:00
2026-08-01 02:36:32 -04:00
2026-07-23 17:45:23 -04:00
2026-02-03 13:52:36 +08:00
2026-07-28 19:08:18 -04:00
2026-07-08 11:27:52 -07:00
2026-05-28 22:41:58 -04:00
2026-05-16 17:21:07 -04:00
2026-08-01 02:18:10 -04:00
2026-07-31 13:24:31 -04:00
2026-08-02 13:31:55 -04:00
2026-07-15 22:40:52 +03:00
2026-07-31 13:24:31 -04:00
2026-02-12 22:36:53 -05:00
2026-07-31 13:24:31 -04:00
2026-06-29 17:41:31 -04:00
2026-08-03 15:10:21 -07:00
2026-07-20 14:31:20 -07:00
2026-08-01 02:18:10 -04:00
2026-02-03 13:52:36 +08:00
2026-07-31 13:24:31 -04:00
2026-05-26 18:15:00 -07:00
2026-07-28 16:51:41 -07:00
2026-08-01 02:18:10 -04:00
2026-04-24 23:40:53 +03:00
2026-07-28 19:08:18 -04:00
2026-02-03 20:20:20 +08:00
2026-02-10 15:08:50 +08:00
2026-02-03 13:52:36 +08:00
2026-04-24 23:40:53 +03:00
2026-07-31 13:24:31 -04:00
2026-08-01 02:18:10 -04:00
2026-07-31 13:24:31 -04:00
2026-07-10 15:13:01 -04:00
2026-02-03 20:20:20 +08:00
2026-05-16 17:21:07 -04:00
2026-07-31 13:24:31 -04:00
2026-04-24 23:40:53 +03:00
2026-07-27 10:07:00 -04:00
2026-03-04 12:58:47 -05:00
2026-07-31 13:24:31 -04:00
2026-08-02 13:31:55 -04:00
2026-07-31 13:24:31 -04:00
2026-07-31 19:56:37 -04:00
2026-08-01 02:18:10 -04:00
2026-07-31 13:24:31 -04:00
2026-08-02 13:31:55 -04:00
2026-08-02 13:31:55 -04:00
2026-05-19 16:35:24 -07:00
2026-07-31 13:24:31 -04:00
2026-08-02 13:31:55 -04:00
2026-07-23 13:02:42 -04:00