coffee/DeepInfer
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepInfer.git synced 2026-10-30 07:47:10 +08:00
Code Issues Packages Projects Releases Wiki Activity
7 Commits 2 Branches 0 Tags Apache-2.0 15 MiB
Commit Graph

7 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
akauncle
d854ba4c92
Merge 0e80d7c835ab1f022b1e3949414aebfa5ee1dc14 into 553741557a57df44a46fb3ab72b6aafeaf945337 2026-10-26 10:06:07 -07:00
Inference_
553741557a
fix: validate boolean environment variables with strict parsing (#218) 2026-10-25 19:59:27 +08:00
uncle
0e80d7c835 fix(examples): honor DEEPINFER_USE_NEXTN_DECODE draft length 
offline_inference.py and benchmark.py wrap the env value in min(1, ...),
which caps lookahead_tokens at 1 for any configured value above zero.
The README documents DEEPINFER_USE_NEXTN_DECODE as controlling the
maximum draft length (default: 5), so pass the configured value through.

Co-Authored-By: Claude Code <noreply@anthropic.com>
 2026-10-21 16:58:12 +08:00
Shaoyuan CHEN
9bd9cf243f
Bump DeepEP to f6aa38fe and drop the SSH->HTTPS rewrite (#157) 
DeepEP now records an HTTPS DeepJIT URL, so build_vendor no longer needs the git@github.com rewrite.

Co-authored-by: Shaoyuan Chen <chensy@deepseek.com>
 2026-10-21 12:55:43 +08:00
hkeee21
774ce244b8 update Q&A EN doc 2026-10-20 19:03:13 +08:00
Jiashi Li
8b16149741 update Q&A documentation 2026-10-20 17:06:57 +08:00
Jiashi Li
d585e6542c initial commit 2026-10-20 12:09:42 +08:00