index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
pplx_server.c
(
follow
)
Commit message (
Expand
)
Author
Age
Files
Lines
*
chore: address static analyzer warnings
Onur Gündüz
2026-06-14
1
-6
/
+28
*
server: expose worker stage timing
Onur Gündüz
2026-06-14
1
-13
/
+95
*
tokenizer: add reusable encode workspace
Onur Gündüz
2026-06-14
1
-1
/
+10
*
server: support http keep-alive
Onur Gündüz
2026-06-14
1
-11
/
+98
*
mlx: add opt-in 8-bit weight quantization
Onur Gündüz
2026-06-14
1
-1
/
+15
*
server: bound mlx batches by padded token rows
Onur Gündüz
2026-06-14
1
-2
/
+25
*
server: reject unsafe mlx model overcommit
Onur Gündüz
2026-06-14
1
-0
/
+103
*
server: simplify context separator logic
Onur Gündüz
2026-06-14
1
-13
/
+4
*
server: batch contextual document inference
Onur Gündüz
2026-06-14
1
-179
/
+354
*
server: batch standard requests by token budget
Onur Gündüz
2026-06-14
1
-11
/
+64
*
server: align embedding quantization with perplexity
Onur Gündüz
2026-06-14
1
-13
/
+11
*
server: support float embedding responses
Onur Gündüz
2026-06-14
1
-18
/
+52
*
server: add embeddings micro-batching
Onur Gündüz
2026-06-14
1
-98
/
+343
*
server: implement HTTP API with libae integration
Onur Gündüz
2026-06-14
1
-0
/
+1524