Commit Graph
226 Commits
Author SHA1 Message Date
LumpiastyandClaude Opus 5.5 2874dcb107 server: disk prompt cache, save slots on shutdown and restore after a restart
llama-swap SIGTERMs a model when the owner switches models (only one large
model fits in RAM), and switching back re-prefills the whole conversation:
about 150 s for a 30k-token chat on the 35B. With --cache-disk-path DIR,
each slot with a prompt is saved to DIR on shutdown. After the restart, a
request whose prompt starts with a saved prompt is restored from the file,
so only the suffix is processed. Off by default.

Save, in server_context::start_loop() after the loop returns:
- disk_cache_collect() copies the state of each slot with >= 256 text tokens
  to host memory (llama_state_seq_get_data_ext, flags NONE) while the device
  buffers still exist. A cold server reads its released state through
  llama_context_restore_memory_host(), with no device use and no extra copy.
- vram_share_exit() then frees the VRAM and releases the GPU token as before,
  so only the D2H copy delays the token release, never the disk IO.
- disk_cache_flush() writes the files. A slot is skipped if its KV does not
  cover its token list (seq_pos_max + 1 != n_tokens: the last batch was not
  decoded) or if the same token list is already on disk.

File (server_prompt_disk_cache, server-task.cpp):
- A 48-byte header (magic, version, key hash, sizes, payload hash), then a
  payload of 8-byte padded sections: tokens, checkpoint table, state, the
  checkpoint states. The hash is FNV-1a over the 64-bit words of the payload.
- Plain fwrite to <name>.tmp, fdatasync, POSIX_FADV_DONTNEED, rename. The read
  is a plain fread plus DONTNEED. There is no mmap: upstream #28092 livelocked
  the kernel on AMD + Vulkan by DMA-ing into a MAP_SHARED file.
- The index is built at startup from the headers. A bad magic, a size that
  does not match the header, or an inconsistent table means the file is
  removed. A hash mismatch at load also removes it, and nothing is restored.
  Other keys and other versions are kept. A .tmp older than 1 h is removed.
- --cache-disk-size N MiB (default 4096, 0 = no limit): before a write, the
  least recently used *.lpcd files of every model in DIR are removed until the
  new file fits; a restore updates the file mtime. Entries the new prompt
  extends are dropped after the write and do not count against the limit.
  A write also needs its size + 1 GiB free on the file system. A write error
  or a full disk is logged; the file is not saved and the exit stays clean.

Key: the build commit, the model path + size + mtime, LoRA and control
vectors, n_ctx, n_ctx_seq, n_seq_max, n_ubatch, kv_unified, swa_full, the
K/V types, the flash-attn type, and the RoPE/YaRN parameters.

Restore, in get_available_slot() after the RAM cache:
- Only while warm (holding the GPU token), with cache_prompt on and no media
  tokens. The file must reuse at least 256 more tokens than the slot holds.
- Reusable means one of two things. Either the saved token list is an exact
  prefix of the new prompt, or (for a recurrent/SWA model) a saved checkpoint
  at or below the common prefix can be used. A plain-KV model can be cut back
  to any prefix. Exact prefix alone is not enough for OpenWebUI on Qwen: the
  template rewrites the previous assistant turn (the reasoning is dropped), so
  the saved list is almost never a prefix of the next turn. The checkpoints
  are exact snapshots, and update_slots() rolls back to one exactly as it does
  for the RAM cache. They are restored with id_task -1, so one that fails to
  load means a re-prefill, not an abort.
- The slot's current prompt goes to the RAM cache first. A set_data failure
  clears the slot and removes the file.

Not supported with speculative decoding (warning, disabled): the draft state
is not saved. Only the slots are saved, not the RAM cache entries.

Measured on the pod, CPU only, Qwen3.5-0.8B (hybrid, 6 of 24 layers attention):
- 573-token chat: 64.5 MiB file with 2 checkpoints, copy 18 ms, write 171 ms,
  exit 314 ms (125 ms without the cache). After the restart: read 166 ms,
  restore 3 ms, turn 2 prompt_n 58 of 596 in 462 ms against a 2913 ms full
  prefill. The answer is identical to a server that never restarted.
- 12k tokens: 200.7 MiB, copy 110 ms, write 350 ms, exit 641 ms, peak RSS
  +162 MiB during the exit save. After the restart: read 307 ms, restore 18 ms,
  turn 2 prompt_n 35 of 12188 in 1.2 s against a 72 s prefill.
- The /root PVC writes at about 0.66 GB/s with fdatasync. /tmp (the node
  overlay) stalled once: 5.8 s for 64.5 MiB.
llama-swap v239 waits for the old process to exit before it starts the next
model, and SIGKILLs a process that is still there after 30 s. So the exit
save adds to the model switch time: about 1 s per GB on the PVC.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 18:55:57 +01:00
LumpiastyandClaude Opus 5.5 f5c0d8f28a server: fix stale VRAM-arbiter comments and the sleep log line
Comments only, plus one log string:
- the arbiter block comment said the KV cache is never evicted; with
  LLAMA_SLEEP_EVICT_KV it is (and the scheduler and scratch with it)
- vram_go_cold said vram_ensure_warm() rebuilds the encoder; only
  encode_mtmd_chunk() restores it, and only for an encode
- vram_ensure_warm and the mtmd init block named process_mtmd_chunk; the
  restore lives in encode_mtmd_chunk
- handle_sleeping_state said waking happens lazily before decode; it
  restores eagerly on the wake transition, before update_slots()
- the vram_cold ordering note now says why it still holds with the inline
  want-lock probe
- the sleep log line said "keeping KV cache" even when LLAMA_SLEEP_EVICT_KV
  evicts it; it now names what actually happens (the prefix
  "server entering sleeping state" that fork-validate.sh counts is kept)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 00:30:20 +02:00
LumpiastyandClaude Opus 5.5 6c480f7e70 server: release the GPU token promptly on shutdown
Two ways a shutting-down server kept the VRAM arbiter's token, stalling every
other model:

- SIGTERM with a request in flight: terminate() stopped only the task queue.
  The HTTP handler kept waiting for results the loop would never send, the main
  thread blocked joining it, and the token was released only in the destructor
  after that join - i.e. never, until the client went away. Terminate the
  result queue too (readers now get "server is shutting down": a 503, or an SSE
  error event), and let wait_until_no_sleep give up once stopping.

- SIGTERM while waiting for the token: the loop thread sat in a blocking flock
  inside the wake callback, holding mutex_tasks, so terminate() waited for the
  current holder to finish and then for a pointless restore of our weights.
  Poll the lock non-blocking and abort the wait on shutdown; the aborted wake
  stays cold, skips the restore, and the loop exits before update_slots.

Also release the token right after start_loop() returns rather than in the
destructor, and only after the device buffers are actually freed: the old
order unlocked before destroy(), so the next model could start uploading into
VRAM that was still occupied. Freeing at exit uses a new
llama_context_discard_device(), which drops weights, KV, MoE cache and scratch
without capturing host shadows first.

Off production: SIGTERM mid-generation or mid-wait now exits in ~0.2 s with
exit 0 and frees the token within 5-70 ms (previously never / after the
holder's whole generation). Handoff latency and greedy output are unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 18:33:19 +02:00
LumpiastyandClaude Opus 5 878d1338f4 server: replace the VRAM doorbell with a want-lock
The doorbell was edge-triggered: a waiter wrote <arena>/doorbell/<pid> and the
holder's warden turned the inotify event into a queue flag. A ring carried no
notion of "still wanted", so it was lost whenever the holder was not already warm
and listening - during its model load (the watch does not exist yet, and the
kernel does not queue events for a watch that is not there) or inside
restore_device - and any ring that survived past the point its sender had been
satisfied caused a spurious release. Lost rings wedged the waiter permanently,
because flock(LOCK_EX) never times out and, with idle-sleep disabled, the holder
had no other reason to release. The wait blocks under mutex_tasks, so the whole
server stopped answering while /health still returned 200.

Express the request as kernel state instead. A waiter holds <arena>/want.lock
shared while it waits and drops it once it owns the token; the sleep decision
probes that lock non-blocking and releases the GPU while anyone is waiting. The
probe needs its own fd - flock treats two open file descriptions of one file
independently, so probing on the waiter's fd would convert our own lock rather
than conflict with it. Nothing can be missed, nothing goes stale, and a waiter
that dies is cleaned up by the kernel.

Probe from should_sleep() on the loop thread rather than from a warden thread.
Routing it through a flag is what made the first attempts fail: start_loop()
holds mutex_tasks from should_sleep() through the callbacks to the wait, so a
warden's request_yield() blocks on that mutex and is admitted only after the flag
has been consumed, latching a release for the next wake. Reading live state where
the decision is made has no edge to latch, and drops the warden's poll latency.

Two sleep-path bugs this exposed: wait_until_no_sleep() waited on !sleeping but
the loop clears req_stop_sleeping on the way in, so a loop that slept again
before the waiter ran stranded it forever - re-ask on every wake. And a task
queued after the waiter saw us awake could not wake us by itself, so sleep now
also breaks on a non-empty queue. Hold the GPU for 100 ms after a wake: the
request that woke us is not queued yet, and yielding at once only sends it round
again.

Measured on the RX 580 pod, two servers contending, 60 alternating handoffs:
0 stranded, median 0.309 s against the doorbell's 0.314 s.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PZz44SLQvTXMyWGio6t9DZ
2026-10-24 18:33:19 +02:00
Lumpiasty 5e99ac1982 server: on-demand mmproj - free encoder VRAM on the text path
The vision encoder sits idle in VRAM on every text request. With
LLAMA_MMPROJ_ONDEMAND=1 the server keeps the encoder in RAM (released
after load) and brings it into VRAM just-in-time before mtmd_batch_encode,
releasing it again afterwards - so the encoder's VRAM is free for KV /
expert cache on the common text-only path.

When the encoder does not fit (that VRAM has been claimed), evict the LLM
backbone weights first: they are not needed while the encoder runs (the
decode that uses them happens afterwards), their host shadow is read-only
(cheap free, no D2H), and the KV / prompt cache is left untouched. Order
on the way back matters: free the encoder before re-uploading the weights
so the peak stays within VRAM.

Also wire the encoder release/restore into the VRAM arbiter: vram_go_cold
releases it; the just-in-time encode-path restore replaces the previous
restore in vram_ensure_warm.

Assisted-by: Claude
2026-10-24 18:33:19 +02:00
Lumpiasty 2feb6aeb27 server: restore weights/KV on wake, not at decode, so KV eviction is safe
With LLAMA_SLEEP_EVICT_KV the KV cache device buffers are freed when a model
goes cold. update_slots() touches the KV before the decode-time vram_ensure_warm
(e.g. SWA models create a checkpoint that reads the KV via ggml_backend_tensor_get),
so the KV must already be resident by then. Move the restore to the sleep-wake
handler (handle_sleeping_state(false)), which runs before update_slots, fixing a
GGML_ASSERT(buffer) crash on iSWA models (gemma) when KV eviction is enabled.

Assisted-by: Claude
2026-10-24 18:33:19 +02:00
Lumpiasty b9df854de8 server: coordinate model load with the VRAM arbiter to avoid load-time OOM
Before uploading a model's weights, acquire the shared VRAM token (ring the
doorbell so any resident model releases first). Previously load uploaded weights
to VRAM before the arbiter was active, so loading a large model while another
(e.g. the warm 4B task model) held VRAM could exceed the budget and OOM.

- add vram_arena_open() (idempotent flock/doorbell setup) and
  vram_acquire_for_load(), called from load_model() before
  common_init_from_params().
- a coordinated load now stays warm holding the token and serves its first
  request without a re-warm (drop the init-time go_cold cold-start).

Assisted-by: Claude
2026-10-24 18:33:19 +02:00
Lumpiasty 958257cd60 server: keep the sleep-wake path active when the VRAM arbiter is enabled
The request handler only calls wait_until_no_sleep() (which wakes a server out
of its sleeping state) when sleep_idle_seconds >= 0. But the VRAM arbiter's
cross-process doorbell can put a server to sleep even when idle-sleep is
disabled, so without this a doorbell-slept server would never wake and requests
to it would hang until timeout.

Do not bypass the wake path when LLAMA_SLEEP_VRAM_ONLY is set, so the arbiter no
longer depends on --sleep-idle-seconds being configured.

Assisted-by: Claude
2026-10-24 18:33:19 +02:00
Lumpiasty 17165fe2a7 server: optionally evict the KV cache too (Phase 2 of VRAM sharing)
Extend on-demand device residency to the KV cache so that when a model's KV
plus another model would not fit in VRAM, the KV can also be evicted to a host
shadow (D2H on release, H2D on restore) instead of only the weights.

- llama_memory_i: add release_device_buffers()/restore_device_buffers()
  (default no-op). Implemented in llama_kv_cache (D2H shadow of the live
  ctxs_bufs, freed and reallocated like the weights); llama_memory_hybrid and
  llama_kv_cache_iswa delegate to their child caches.
- llama_context::release_device(evict_kv): also evict the memory's device
  buffers when requested; restore_device() rebuilds them. Public API
  llama_context_release_device gains an evict_kv flag.
- server: LLAMA_SLEEP_EVICT_KV=1 enables it. Off by default (weights-only),
  since the KV shadow adds a D2H/H2D copy of the live cache each cycle.

Validated on RX 580 (Vulkan), 4B @ 32k ctx: weights-only cold VRAM 1750 MB
(KV stays); weights+KV cold VRAM 726 MB (KV freed, ~1 GB reclaimed). KV
survives the round-trip: prompt cache reused after the cycle (prompt_n 4 vs
42), correct output.

Assisted-by: Claude
2026-10-24 18:33:18 +02:00
Lumpiasty 481be8b284 server: on-demand VRAM sharing to time-share one GPU between models
Add release/restore of a model's GPU weight buffers (keeping a host shadow
and the KV cache) so several always-loaded llama-server processes can
time-share a single GPU without reloading or losing the prompt cache.

- llama-model: release_device_weights()/restore_device_weights() capture a
  compact host shadow (stable iteration order, view-skipping) and free then
  realloc the device weight buffers; weights_resident() query.
- llama-context: release_device()/restore_device() wrappers; decode() auto-
  restores; public C API llama_context_release_device/restore_device.
- server: LLAMA_SLEEP_VRAM_ONLY makes idle-sleep release only the VRAM weights
  (not a full unload/reload). A cross-process flock token in LLAMA_VRAM_ARENA
  enforces "resident iff holds token"; an inotify doorbell forces the holder
  to release on contention. The warden thread only touches the task queue, so
  releases run on the loop thread and never race a decode.

Validated on RX 580 (Vulkan): two models share 8GB, never both resident,
correct output under contention, KV cache preserved (no re-prefill).

Assisted-by: Claude
2026-10-24 18:33:18 +02:00
Xuan-Son NguyenandPascal d814cbb88c server: realtime API: send complete after committed audio drains (#30994)
* server: realtime API: send complete after committed audio drains

* server: realtime API: complete a commit at its end row

Completion is triggered when the stream runs dry, which is a timing
proxy: audio appended while the tail drains leaks into the committed
item, a final commit before the drain merges both items, and back to
back commits collapse into one.

mtmd_audio_stream_flush() records the row count at the end of the
flushed audio (mtmd_audio_stream_get_n_rows_flushed), next to the rows
produced so far (mtmd_audio_stream_get_n_rows). The slot keeps a FIFO
of these end rows and completes each commit once every row up to it is
decoded.

---------

Co-authored-by: Pascal <admin@serveurperso.com>
2026-10-23 00:37:47 +02:00
Tim Wangandtimothywang21 a5d22276be server : support typed content input for RERANK endpoint (#29625)
* server : support typed content input for rerank endpoint

Assisted-by: Opencode/Qwen3.8 27B

* server : address rerank multimodal review findings

- reject multimodal rerank input when the model has no rerank chat template (images were silently dropped)
- translate handle_media download/base64 failures to 400 instead of 500
- reject negative top_n with 400 instead of letting resize throw
- fix comment typos, redundant comments, indentation and trailing whitespace
- README: document that TEI input accepts the same shape as Jina; drop stray blank line

Assisted-by: opencode

* Trimmed README

---------

Co-authored-by: timothywang21 <timothywang21@users.noreply.github.com>
2026-10-22 13:27:24 +02:00
Unbug Lee 9a3b91c680 server : fix usage.completion_tokens undercount with n > 1 (#29486)
Assisted-by: Copilot
2026-10-21 01:19:54 +02:00
Xuan-Son NguyenandPascal 5c0b49a23b server : add POST /tts endpoint for TTS models (#26603)
* mtmd: add audio out stream api

* add /tts endpoint

* add docs

* wire up mtmd_helper_model_can_chat

* upload speaker_ref via form-data

* expose seed to api

* fix header for pcm

* wip

* fix penalty_last_n

* fix server_output_limits

* fix pocket-tts stream

* wip

* add server_schema for tts

* add server routing

* server: coerce seed and stream from multipart form fields

Form fields arrive as strings, so -F seed=42 and -F stream=true were
rejected by the schema. seed joins the integer fields, parsed as a long
long so a full uint32 seed fits, and stream is read as a boolean when
it comes as a string.

---------

Co-authored-by: Pascal <admin@serveurperso.com>
2026-10-21 01:19:42 +02:00
Xuan-Son NguyenandPascal 1242be66f6 server: add realtime transcription API (#30636)
* server: add realtime transcription API

* drop transcription_sessions

* proxy ws

* add docs

* server: let the API key middleware guard the websocket

httplib runs the pre-routing handler before the websocket upgrade, so
the API key middleware answers 401 at handshake like any other route.
This covers the router proxy, whose children run keyless, and accepts
the same key forms as HTTP (Bearer, raw key, X-Api-Key).

* server: keep realtime slots out of the prompt loop

A realtime slot waiting for audio is GENERATING with nothing to decode,
so it fell through the prompt loop and took slot_batched. A request on
a higher slot then failed can_batch_with on the task type and starved
for the whole session. Realtime slots have no prompt: the loop sets
them up once and always leaves them.

* server: start the realtime session once its slot is live

The audio stream was created in the prompt loop, which skips a slot
that cannot batch with the one generating, and session.created went out
before the task was posted: early appends failed and the reader quit,
leaving the socket open and the slot held until the HTTP timeout.

The slot now sets up its stream at launch and signals it with the begin
result, session.created waits for it, and a reader that stops closes
the socket so the session ends with it.

* server: name the committed item in input_audio_buffer.committed

Per the Realtime spec, item_id is the item made from the committed audio
and previous_item_id the one committed before it, null for the first.
committed now comes before the transcript that completes that item, and
both go out with the item switch under one lock, so a delta cannot land
between them.

* server: use the GA transcription session shape

The session object follows the GA Realtime schema: type transcription,
with the input format, transcription model, turn detection and noise
reduction under audio.input. The rate stays the model sample rate, which
is what the client must send for now.

---------

Co-authored-by: Pascal <admin@serveurperso.com>
2026-10-21 00:04:15 +02:00
ead9f32058 server: Support logprobs with speculative decoding (#27196)
* return logprobs in spec path

* server: add regression test for logprobs with speculative decoding

Asserts accepted draft tokens report the target model's logprobs,
comparing a draft-enabled run against a no-draft baseline (#24271).
Fails on master (top_logprobs empty, logprob 0.0), passes with the
fix from #27196.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KARBWpPcijcBXzJEvttuwk

---------

Co-authored-by: Jeonghyun Lee <sig.jhl@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-10-20 19:36:14 +02:00
7e3eeee048 model : add H2O-Lightning-4B decision model (#30361)
* model : add H2O-Lightning-4B decision model

Adds the h2o-lightning decision type for h2oai/h2o-lightning-4b
(Qwen3.5-4B with a merged decision LoRA).

None of the existing types match this model. It answers with " A"
rather than "A", uses up to 255 labels, and was trained on Python
json.dumps text, so floats like 12.0 must render as 12.0.

The converter writes the decision metadata and the systemone template
from the model's serve_config.json and refuses a config that doesn't
match. Tests skip unless the tiny test model is available locally.

Assisted-by: Claude Opus 5.5

* rm redundant code

* put labels to gguf

---------

Co-authored-by: Jonathan C. McKinney <jon.mckinney@h2o.ai>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-10-20 18:54:27 +02:00
TANGBUDUandTANGBUDU 5a9a34d888 server : avoid repeated mmproj memory margin addition on sleep/resume (#28233)
Co-authored-by: TANGBUDU <TANGBUDU@users.noreply.github.com>
2026-10-20 18:32:12 +02:00
7adf160c41 server: add --connect, allow p2p access to server outside LAN (#28277)
* init

* wip

* wire it up

* make it clear that it's experimental

* add props.connect_code

* nits

* fix windows build

* server: do not advertise a connect code without the tunnel

--connect-code on its own had no effect other than being served in
/props, so the Web UI showed a remote access code that no tunnel was
serving. Clear it when --connect is off, and say so once at startup.

The teardown comment claimed that terminate() closes the child stdout.
It does not: the log thread leaves fgets() only once every writer of
that pipe is gone, so a descendant of llama-connect would block the
join forever. Describe the real contract instead.

Also restore the --reasoning-preserve default in the generated docs.

* Update tools/connect/CMakeLists.txt

Co-authored-by: Adrien Gallouët <angt@huggingface.co>

* server: dial llama-connect on the bound port and a reachable host

Pass ctx_http.port so --port 0 and the GCP override work, pick the
dial host from --host (wildcards map to loopback, IPv6 is bracketed)
and refuse --connect when only unix sockets are bound.

---------

Co-authored-by: Pascal <admin@serveurperso.com>
Co-authored-by: Adrien Gallouët <angt@huggingface.co>
2026-10-20 00:23:14 +02:00
Tarek Dakhran f174553e16 server : fix swa checkpoint invalidation logic (#30666)
* server : fix swa checkpoint invalidation logic

Assisted-by: Claude

* add testcase that fails with > n_past, but works with > n_prefix
2026-10-19 15:58:14 +02:00
Pascal 61ad80bf93 server: fix the off-by-two in the SWA reuse threshold (#30580)
The first evaluated token attends to the positions above
pos - n_swa, so a SWA state starting at pos - n_swa + 1 holds the
whole window, but the reuse threshold asked for two more cells.
A saved SWA state keeps only the cells inside its window, so a
state read back from a slot file or from the RAM prompt cache was
always rejected and the slot rolled back to a checkpoint.

The SWA threshold now matches the window, while a state without SWA
keeps the exact bound. The test harness gains override_kv, used to
give the SWA test model a window smaller than the test context.

[no release]
2026-10-15 16:25:19 +03:00
Pascal ea736c1d5c server: save the draft state in the slot file (#30574)
The slot file held the target context and the context checkpoints,
but never the draft context, so a restored slot drafted with an
empty or stale draft KV until the cache refilled.

The file now ends with the live draft state, the full draft context
and the speculative state, in the same appendix style as the
checkpoints. A draft state that does not fit the draft context is
dropped and the draft starts empty, while older files and older
servers keep working.

[no release]
2026-10-15 16:24:19 +03:00
Pascal b0d239164b server: prefer empty slots and keep states overwritten by child tasks (#30567)
Slot selection takes free slots by id or by last use only, so child
tasks often land on a slot holding a parent state while empty slots
are idle, and overwrite it without saving it to the prompt cache.

Free slots are now ordered empty first, then least recently used, for
both the LRU fallback and the child slots, and a child task saves the
state it overwrites. With 4 grouped decision requests in flight and
12 states in rotation, prompt cache reads go from 5 to 36.

[no release]
2026-10-15 16:24:01 +03:00
Pascal 2639a3b4e0 server: save only restorable slot states to the prompt cache (#30498)
* server: save only restorable slot states to the prompt cache

The idle-slot save loop stores every idle slot whenever a task starts,
while only completion tasks restore from the prompt cache. Rerank,
embedding, decision and infill states fill the cache up to its limit
without ever being read back, and slots already cached are offered
again at every task start.

Each slot now tracks with cache_pending whether its state is restorable
and missing from the cache: a completion release or an explicit slot
restore sets it, prompt_save consumes it, prompt_clear resets it. Both
save paths share this rule, and the LRU path restores only for
completion tasks.

* server: test that decision slots skip the prompt cache

Decision tasks never mark their slot as cacheable, so starting new
tasks must not save their idle slots to the RAM prompt cache, with or
without a unified KV cache.

* server: restore any reusing task from the prompt cache

Embedding and rerank tasks never reuse their state, so their slots are
cleared on release like child slots and the cache only holds states
that a later task can restore. Infill and decision tasks now restore
from the cache too, which replaces the cache_pending flag.

Decision models disable the prompt cache unless --cache-ram is given,
since their states seldom repeat.
2026-10-15 06:30:17 +02:00
Xuan-Son Nguyen efe3626b11 model: support vllm d3 models (#30383)
* models: support pplx-decider

* vllm d2

* update

* clarify naming rule

* stricter validation

* d3
2026-10-12 15:01:52 +02:00
Xuan-Son Nguyen 097cf33d94 model: support vllm decision 2 model (#30378)
* models: support pplx-decider

* vllm d2

* update

* clarify naming rule

* stricter validation

* fix ci

* rm redundant filter_tensors
2026-10-12 13:39:55 +02:00
Georgi Gerganov 972b5fcc19 llama : report compute graph reallocations during inference (#30329)
Add an optional ggml_backend_sched_realloc_callback that user code registers with
ggml_backend_sched_set_realloc_callback to be notified when the buffers reserved for a
graph are not sufficient and have to be reserved again. The callback reports whether the
backend assignments and the graph size changed since the previous scheduling.

llama_context registers the callback when creating the scheduler (wrapped into the new
llama_context::sched_new helper) and treats the reallocations that follow a change of the
backend assignments as expected, counting the rest by graph size - unchanged or changed
from the previously scheduled graph. Both counters are reported on one line in the perf
stats.

Assisted-by: pi:llama.cpp/Qwen3.8-Flash-Next
2026-10-12 11:53:58 +03:00
Pascal 23b0202a18 server: leave a busy slot untouched when a request pins it (#30295)
A request asking for a busy id_slot still ran the prompt cache update
on that slot before being deferred. When the RAM cache held a better
match, it was loaded into the slot while another request was still
generating there, and that generation continued on the wrong context.

The busy slot is now returned as is and the request waits for it.
2026-10-10 21:25:38 +02:00
Aldehir Rojas 8b54361025 chat : refactor API (#30210) 2026-10-09 10:06:22 -05:00
Leebr Data ConsultingandIgor Okulist 033df86b69 server : preserve context checkpoints across slot save/restore (#26004)
* server : preserve context checkpoints across slot save/restore

Append the checkpoints after the packed server_tokens payload added in #26640
and count them in n_written / n_read, so a restored slot can still roll back to
a checkpoint instead of re-processing the whole prompt.

* server : drop draft checkpoint data that does not match the draft context

Restoring a slot saved with a different draft KV cache type aborted in
load_dft(). Test-load one draft checkpoint on restore and drop the draft
data if it does not fit, instead of crashing. Adds a regression test.

Co-authored-by: Igor Okulist <okigan@gmail.com>

* server : harden the checkpoint appendix of slot save files

Bound each blob size by the bytes left in the file before allocating, open the
file with UTF-8 paths on Windows like the llama state payload, fall back to full
prompt re-processing when a checkpoint restored from a slot file fails to load,
and replace the 1024 count cap by keeping the last n_ctx_checkpoints while reading.

* server : report an incomplete checkpoint appendix as a failed slot save

Return an error to the client when the appendix cannot be written, like a
failed payload write, and make the oversized-blob test declare a size that
cannot be allocated, so an unbounded allocation fails the test.

* server : reject an empty target state in the checkpoint appendix

A saved checkpoint always holds a target state, an empty blob would roll back
without restoring anything. Also log with the slot id, and load the draft test
model from the HF cache instead of a second download.

* common : return bool from checkpoint load_tgt / load_dft

A checkpoint restored from a slot file falls back to full prompt re-processing
when it fails to load, a checkpoint created in memory still aborts.

---------

Co-authored-by: Igor Okulist <okigan@gmail.com>
2026-10-08 13:18:20 +03:00
Tarek Dakhran a657f7e981 model : add LiquidAI/d1-omni-600M decision model (#30114)
* model : add LiquidAI/d1-omni-600M decision model

Assisted-by: Claude Opus 5.5

* mtmd : keep conformer GLU sigmoid on CUDA

Assisted-by: Claude Opus 5.5

* server : take d1omni audio through images and input_audio, scope memory-less lfm2 to non-causal

Assisted-by: Claude Opus 5.5

* common : rename decision type d1omni to lfm2-d1-omni, server : make images an alias of files

Assisted-by: Claude Opus 5.5
2026-10-08 02:07:49 +02:00
Tarek Dakhran 88dcc460d6 model : add LiquidAI/d1-3B decision model (#30110)
* model : add LiquidAI/d1-3b decision model

mtmd : read LFM2 image resize algo from GGUF

Assisted-by: Claude Opus 5.5

* common : rename decision type d1 to lfm2-d1

Assisted-by: Claude Opus 5.5
2026-10-07 22:04:39 +02:00
Aldehir Rojas 18b5f8b186 server : accumulate generated text and tokens as parse input (#29876)
* server : collect text and token input

* common : add a tokenize helper that aligns tokens with bytes

* common : simplify tokenize logic
2026-10-07 11:49:17 -05:00
Adrien Gallouët 4d60b4d087 common, server : report model input/output modalities in GET /models (#29987)
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-10-05 17:08:29 +02:00
Xuan-Son Nguyen 9871df5911 server: support vision input for Clef (#29969)
* server: support vision input for Clef

* move input_attn_causal to private

* extend old server_batch::embd

* server_batch::token::pos to multi dim

* nits

* fix abort

* fix img tokens cap

* fix yield_to_queue mutate data
2026-10-05 14:02:40 +02:00
Xuan-Son NguyenandSigbjørn Skjæret 99b95488ca model: add support for clef decision model (text-only) (#29831)
* init support for clef (text only)

* more static graph

* clean up

* nits

* nits 2

* Update gguf-py/gguf/constants.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-10-03 02:50:48 +02:00
1fb7ef3e33 spec : add probabilistic sampling for simple draft and MTP (#27694)
* Make the drafter probabilistic and the target verify by rejection sampling

* Drop stale spec_draft_q before drafting

* Fallback to argmax sampling for grammar-constrained requests and adding flag for enabling probabilistic draft sampling. Default flag value is greedy.

* Support grammar-constrained requests in rejection sampling

* Fix - renormalize distribution after masking

* copy rng on sampler copy and re-accept drafted tokens on replay

* Fix draft sampler sharing the target's rng stream

* Simplify the rejection sampler's inputs and move replay to the server

* Truncate the draft candidates along with the draft

---------

Co-authored-by: praneshgo <227579474+praneshgo@users.noreply.github.com>
Co-authored-by: Pranesh Gonegandla <pgonegandla@nvidia.com>
2026-10-02 17:52:54 +03:00
Xuan-Son Nguyen 46ca246de9 model: support nimble decision model (#29844) 2026-10-02 14:56:53 +02:00
Xuan-Son Nguyen a4cb4c61fd llama, server: add /v1/systemone API (models: laya, julia-1, lev, openjev, kev) (#29818)
* init conversion

* convert: ok

* model loaded

* add server code

* improve conversion script

* support shared prompt prefix

* add docs, imorove UX a bit

* add vision support

* add openjev tiny model for testing

* add dev docs

* support lev & kev

* clean up

* fix lev noul

* fix py lint

* nits docs

* clarify about not supporting date_facts
2026-10-02 11:56:04 +02:00
Xuan-Son Nguyen 552f18f912 mtmd: cap max_image to ubatch for non_causal models (#29773) 2026-10-01 11:55:11 +02:00
Georgi Gerganov c85b92c69c tests : adjust server string regex to also match m2 utlra results (#29648) 2026-09-29 15:32:35 +03:00
680a036285 server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556)
* server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding)

Accept the OpenAI-style wrapped content array format for multimodal
embedding requests. Each {"content": [...]} object is one input that
produces one embedding; text parts are concatenated and image_url parts
are decoded via handle_media then spliced with process_mtmd_prompt.

The legacy formats (plain string, token arrays, mixed arrays, and the
{prompt_string, multimodal_data} object) continue to work unchanged via
tokenize_input_prompts. Bare content arrays (the unwrapped shape) are
rejected with a migration message.

Also disables KV prefix reuse for stateless embedding/rerank tasks so
that repeated inputs do not incorrectly share cached KV across requests.

Assisted-by: Opencode Qwen3.8 27B

* clean up comments and docs

* refactor

* add tests

* support video and audio inp

---------

Co-authored-by: timothywang21 <timothywang21@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-09-28 21:40:38 +02:00
Xuan-Son Nguyen f1ea206218 batch: migrate speculative, mtmd and server to batch_ext (#29385)
* adapt common

* add common_batch

* wip

* wip: spec

* cont

* common_speculative_process

* server_batch to use common_batch

* rm some stale calls

Assisted-by: Claude Fable 5.1

* migrate mtmd

* handle imrope, handle return val of add()/add_embd()

* add spec zeros vector

* add warning on zero fill path
2026-09-28 19:52:45 +02:00
Tim Wangandtimothywang21 4da6337767 server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876)
* server : allow splitting RANK pooling for causal LLM rerankers

Rerank models fall into two categories: bidirectional cross-encoders
(BERT, etc.) that require all tokens in a single physical batch, and
causal LLMs repurposed as rerankers (Qwen3, Qwen3-VL) that can use
chunked prefill like any other decoder.

Previously the server rejected all RANK-pooling inputs larger than
n_ubatch, and the graph builder hardcoded QWEN3/QWEN3VL arch checks to
determine last-token pooling. This broke long-document and multimodal
reranking for causal models.

Fix: expose llama_get_causal_attn(ctx) so the server can check the
effective runtime attention type (reflecting any --attention override
or set_causal_attn call). Also expose llama_model_is_causal(model)
for querying the static architectural property from GGUF metadata.

can_split() now permits chunked prefill for RANK pooling when the
context is causal. The graph builder's inline arch check is replaced
with the same cparams.causal_attn predicate, removing the duplication.

Assisted-by: Opencode/Qwen3.8-27B

* remove unused llama_model_is_causal, fix whitespace

Assisted-by: opencode

---------

Co-authored-by: timothywang21 <timothywang21@users.noreply.github.com>
2026-09-27 23:28:10 +02:00
Adrien Gallouët 2b70583997 server,common : fix the GCC 12 stringop-overread false positive (again) (#29325)
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-09-24 08:40:06 +02:00
Will 42916d83f4 server: fix token counting API crash on sleep (#29309)
* server: wake up sleeping server correctly

* server: wake up sleeping server correctly (local aliases removed)
2026-09-23 15:28:49 +02:00
Jesus Gulfo b0dcb8192b server: fix speculation after an image (#28715)
* server: fix speculation after an image

Pass the actual position to the drafter after an image, instead of the
token count. Affects every drafter, not just DFlash.

* rename draft n_past to pos0

n_past is used to denote number of tokens and this parameter is meant to be a position
2026-09-11 11:33:26 +03:00
Foad Abo Dahood 5d806aa257 server : apply checkpoint min-step eviction only when the checkpoint list is full (#28302)
The spacing eviction in create_checkpoint() keeps the oldest checkpoint and
erases every later one within checkpoint_min_step of it. For prompts shorter
than checkpoint_min_step this drops the checkpoint at n_tokens - 4 that the
next request resumes from, so hybrid/recurrent models re-prefill from the
previous checkpoint instead. Apply the spacing rule only once the list is at
n_ctx_checkpoints, and replace an existing checkpoint at the same n_tokens
instead of appending a duplicate.
2026-09-08 16:01:03 +03:00
Georgi GerganovandXuan-Son Nguyen e750b887a8 common, server : enable preserve_reasoning kwarg by default, log its effective state (#28174)
* common, server : enable preserve_reasoning kwarg by default, log its effective state

If the preserve_reasoning chat template kwarg is not specified explicitly
via --reasoning-preserve / --no-reasoning-preserve, it is enabled by
default after argument processing. The server logs the effective state of
the kwarg, warns that it is enabled by default when the template supports
it, and only warns "has no effect" when it was enabled explicitly on a
template that does not support it. Setting the kwarg via
--chat-template-kwargs is deprecated.

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* cont : update comment

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
2026-09-02 19:19:54 +03:00
BartowskiandXuan Son Nguyen 18443257a3 server: add ctx-per-slot (--kv-unified-per-slot) (#24124)
* Add ctx-per-slot argument for unifid KV cache

* Swap out ctx fractions for ctx pool slots

* Formatting cleanup

* Remove ctx-pool-slots, make ctx-per-slot an int

* refactor it

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-08-27 22:39:14 +02:00