index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
pplx_embed.c
(
follow
)
Commit message (
Expand
)
Author
Age
Files
Lines
*
gitignore: track new binary and library names
Onur Gündüz
2026-06-14
1
-1483
/
+0
*
kernels: drop asr_ prefix naming
Onur Gündüz
2026-06-14
1
-2
/
+2
*
cuda: add initial CUDA embedding backend
Onur Gündüz
2026-06-14
1
-57
/
+1
*
chore: address static analyzer warnings
Onur Gündüz
2026-06-14
1
-2
/
+5
*
late: add packed maxsim scoring
Onur Gündüz
2026-06-14
1
-3
/
+22
*
late: add CPU token vectors and maxsim
Onur Gündüz
2026-06-14
1
-5
/
+188
*
all: add validation for late-interaction model compat
Onur Gündüz
2026-06-14
1
-1
/
+25
*
cpu: reuse tiled attention scratch buffers
Onur Gündüz
2026-06-14
1
-3
/
+23
*
server: batch contextual document inference
Onur Gündüz
2026-06-14
1
-12
/
+69
*
dist: load distributed layer shards selectively
Onur Gündüz
2026-06-14
1
-14
/
+46
*
dist: add distributed layer-slice foundation
Onur Gündüz
2026-06-14
1
-21
/
+113
*
api: add opt-in l2 normalization helper
Onur Gündüz
2026-06-14
1
-3
/
+31
*
server: align embedding quantization with perplexity
Onur Gündüz
2026-06-14
1
-23
/
+5
*
server: implement HTTP API with libae integration
Onur Gündüz
2026-06-14
1
-0
/
+62
*
cpu: keep batch offsets in workspace
Onur Gündüz
2026-06-14
1
-10
/
+38
*
cpu: tighten workspace growth
Onur Gündüz
2026-06-14
1
-4
/
+14
*
cpu: reduce initial workspace capacity
Onur Gündüz
2026-06-14
1
-1
/
+2
*
server: report workspace memory
Onur Gündüz
2026-06-14
1
-0
/
+58
*
kernels,cpu: fuse tiny BF16 gate up projections
Onur Gündüz
2026-06-14
1
-3
/
+26
*
kernels,cpu: fuse small BF16 QKV projections
Onur Gündüz
2026-06-14
1
-3
/
+24
*
cpu: reuse MLP scratch buffer
Onur Gündüz
2026-06-14
1
-6
/
+3
*
cpu: support BF16 weights
Onur Gündüz
2026-06-14
1
-46
/
+142
*
cpu: fuse CPU embedding hot paths
Onur Gündüz
2026-06-14
1
-11
/
+23
*
cpu: validate model tensor shapes
Onur Gündüz
2026-06-14
1
-21
/
+90
*
cpu: harden workspace allocation
Onur Gündüz
2026-06-14
1
-41
/
+125
*
api: simplify embedding API
Onur Gündüz
2026-06-14
1
-80
/
+46
*
api: split model and workspace ownership
Onur Gündüz
2026-06-14
1
-98
/
+203
*
all: support batched embedding attention
Onur Gündüz
2026-06-14
1
-81
/
+180
*
Refactor and enhance pplx_embed and pplx_embed_mlx for improved model support
Onur Gündüz
2026-03-28
1
-219
/
+240
*
Init
Onur Gündüz
2026-03-28
1
-0
/
+447