index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
embed.c
(
follow
)
Commit message (
Collapse
)
Author
Age
Files
Lines
*
chore: move sources to src/ with proper names, drop qwen_ prefix
Onur Gündüz
2026-06-16
1
-1815
/
+0
|
*
all: support BERT tanh-GeLU (gelu_new / gelu_pytorch_tanh)
Onur Gündüz
2026-06-16
1
-1
/
+4
|
*
cpu: add the BERT encoder family forward and loader
Onur Gündüz
2026-06-15
1
-16
/
+229
|
*
all: add CLS first-token pooling
Onur Gündüz
2026-06-15
1
-4
/
+10
|
*
all: support GTE-Qwen2 embeddings
Onur Gündüz
2026-06-15
1
-4
/
+29
|
*
api: share config parsing across backends
Onur Gündüz
2026-06-15
1
-146
/
+2
|
*
api: accept Hugging Face model weight prefix
Onur Gündüz
2026-06-15
1
-28
/
+38
|
*
late: add CUDA late-interaction rerank path (GPU encode, host MaxSim)
Onur Gündüz
2026-06-15
1
-0
/
+10
|
*
late: batch CPU rerank candidate encoding in one packed forward
Onur Gündüz
2026-06-15
1
-0
/
+92
|
*
chore: run clang-format
Onur Gündüz
2026-06-15
1
-516
/
+532
|
*
all: add Qwen3-Embedding-4B + fix terminal token
Onur Gündüz
2026-06-14
1
-6
/
+1
|
*
all: add support for Qwen3-Embedding + causal GQA attention
Onur Gündüz
2026-06-14
1
-26
/
+85
|
*
chore: rename project
Onur Gündüz
2026-06-14
1
-146
/
+146
|
*
dist: remove distributed layer-sharding (protocol, CLI flags, slice APIs)
Onur Gündüz
2026-06-14
1
-42
/
+0
|
*
late: batch MaxSim as grouped GEMM plus row-max reduction
Onur Gündüz
2026-06-14
1
-2
/
+60
|
*
cpu: move BF16 widening scratch into the workspace
Onur Gündüz
2026-06-14
1
-18
/
+49
|
*
chore: rename sources; binaries pplx-embed, pplx-embed-server
Onur Gündüz
2026-06-14
1
-2
/
+2
|
*
gitignore: track new binary and library names
Onur Gündüz
2026-06-14
1
-0
/
+1483