index
:
ffwd
master
Fastforward embedding inference engine
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
embed_server.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
-3725
/
+0
|
*
cpu: size default threads to cgroup cpu quota, not host core count
Onur Gündüz
2026-06-16
1
-1
/
+1
|
*
server: register bge-base and bge-large encoders
Onur Gündüz
2026-06-16
1
-0
/
+6
|
*
server: serve BERT encoders (MiniLM, bge) on /v1/embeddings
Onur Gündüz
2026-06-15
1
-40
/
+117
|
*
server: guard empty-chunk memcpy and check self-pipe writes
Onur Gündüz
2026-06-15
1
-4
/
+12
|
*
all: support GTE-Qwen2 embeddings
Onur Gündüz
2026-06-15
1
-38
/
+41
|
*
server: add Qwen3 text_type query/document instruction hint
Onur Gündüz
2026-06-15
1
-2
/
+71
|
*
late: add CUDA late-interaction rerank path (GPU encode, host MaxSim)
Onur Gündüz
2026-06-15
1
-9
/
+75
|
*
late: batch CPU rerank candidate encoding in one packed forward
Onur Gündüz
2026-06-15
1
-20
/
+23
|
*
late: batch MLX rerank candidate encoding in one padded pass
Onur Gündüz
2026-06-15
1
-30
/
+23
|
*
chore: run clang-format
Onur Gündüz
2026-06-15
1
-636
/
+664
|
*
server: version flags, drop cost block, tidy batch-wait note
Onur Gündüz
2026-06-15
1
-30
/
+35
|
*
server: per-family embedding encoding (Qwen3 float, pplx int8)
Onur Gündüz
2026-06-14
1
-57
/
+99
|
*
server: add Qwen3-Embedding-8B model slot
Onur Gündüz
2026-06-14
1
-0
/
+3
|
*
all: add Qwen3-Embedding-4B + fix terminal token
Onur Gündüz
2026-06-14
1
-6
/
+8
|
*
all: add support for Qwen3-Embedding + causal GQA attention
Onur Gündüz
2026-06-14
1
-28
/
+108
|
*
docs: fix CLI name in comments
Onur Gündüz
2026-06-14
1
-4
/
+1
|
*
cli: scope GPU options to their respective build targets
Onur Gündüz
2026-06-14
1
-68
/
+77
|
*
server: remove CORS support
Onur Gündüz
2026-06-14
1
-11
/
+1
|
*
cli: remove --backend, use --mlx and --cuda consistently
Onur Gündüz
2026-06-14
1
-36
/
+7
|
*
server: add late-interaction rerank API
Onur Gündüz
2026-06-14
1
-42
/
+595
|
*
server: tune admission deadline by backend
Onur Gündüz
2026-06-14
1
-2
/
+5
|
*
server: make microbatch admission deterministic
Onur Gündüz
2026-06-14
1
-30
/
+68
|
*
chore: rename project
Onur Gündüz
2026-06-14
1
-128
/
+128
|
*
server: resolve contextual separator from vocab, test contextual path
Onur Gündüz
2026-06-14
1
-1
/
+8
|
*
build: rename make targets blas->cpu, mlx->metal, shared->lib
Onur Gündüz
2026-06-14
1
-2
/
+2
|
*
server: default micro-batch cap to 32; add scheduler sweep driver
Onur Gündüz
2026-06-14
1
-3
/
+6
|
*
server: do not idle-reap clients with requests in flight
Onur Gündüz
2026-06-14
1
-1
/
+4
|
*
chore: rename sources; binaries pplx-embed, pplx-embed-server
Onur Gündüz
2026-06-14
1
-4
/
+339
|
*
gitignore: track new binary and library names
Onur Gündüz
2026-06-14
1
-0
/
+2431