10 Commits
Author SHA1 Message Date
fedb48fa74 mtmd: add MiniMax M3 vision support (#2086)
Co-authored-by: Smart <smart@augmented-special.services>
2026-07-12 07:19:14 +03:00
3bb0e9f09c fix: MiniMax-M3 streaming parser when tool calls start before </mm:think> (#2085)
* fix: improve MiniMax-M3 streaming parser

* fix: guard MiniMax-M3 tool args against marker leaks

---------

Co-authored-by: Smart <smart@augmented-special.services>
2026-07-09 18:12:47 +03:00
Jun YamogandGitHub 33dabeae21 Normalize disabled context-shift overflow error (#2051) 2026-06-29 08:30:05 +02:00
Jun YamogandGitHub 69a8336d08 Add native MiniMax-M3 tool call parser (#2008) 2026-06-23 09:36:02 +02:00
Jun YamogandGitHub 064d23a6f8 Codex CLI Responses Compatibility (#1964)
* responses: skip known unsupported Responses tool types from Codex CLI

- Skip namespace, web_search, image_generation tools instead of HTTP 500
- Reject unknown non-function tool types with controlled error
- Preserve function tool conversion logic unchanged

Fixes Codex CLI 0.133.0 compatibility where it sends mixed tool types.

* responses: harden codex compatibility coverage

* responses: expose Codex model catalog metadata
2026-06-16 15:28:16 +02:00
Jun Yamog c08d194edd Use standard graph helpers for MiniMax-M3 2026-06-15 02:00:46 +00:00
Jun Yamog c538210e6d Add MiniMax-M3 chat template 2026-06-15 01:29:13 +00:00
Jun Yamog 0df00b3b94 Add preliminary MiniMax-M3 support 2026-06-14 12:23:20 +00:00
Jun YamogandGitHub 53cd4d0ff0 fix: use mmq for volta quantized matmuls (#1785) 2026-05-15 08:11:49 +03:00
Jun YamogandGitHub 8b0cd0357a fix: keep sm70 cublas f32 outputs in f32 (#1776) 2026-05-12 07:38:42 +03:00