6f74ba3807
mtp-batch (fix): prevent mtp draft from polluting the cache
2025-10-09 22:27:18 -03:00
5e1d719bef
mtp-batch (feat): Create and manage sinfo for MTP
2025-10-09 15:21:23 -03:00
67c6c069e0
mtp-batch (wip): Isolate MTP graph to prevent host embedding buffer corruption
2025-09-27 19:42:32 -03:00
75dc25e6fe
mtp-batch (wip): organize batch for mtp cache
2025-09-27 17:17:00 -03:00
3da7e7f330
mtp-batch (fix): warm mtp cache for small batch size
2025-09-23 22:45:11 -03:00
df64508b93
mtp-batch (wip): merge glm graphs
2025-09-21 21:55:41 -03:00
042eb8a829
mtp-batch (wip): merge mtp and model graph
2025-09-21 21:29:00 -03:00
1318b2de82
mtp-batch (wip): move mtp execution to batch format
2025-09-14 10:22:59 -03:00
07670a22c6
feat: implemented sampling for MTP
2025-09-03 13:25:21 -03:00
98bc0c6bf2
replace standard sampler with greedy sampler for mtp draft
2025-08-26 01:26:51 -04:00
471e026327
fixed vram leak
2025-08-19 23:10:56 -04:00
d72f9d5691
kludge-y kv cache management of mtp layer
2025-08-19 01:50:34 -04:00
6870f9790c
added proper KV cache management for MTP layers and slightly refactored
2025-08-17 04:59:36 -04:00
6e9bafc7a7
failed attempt to implement MTP; outputs tokens but KV cache management is unreasonable
2025-08-15 23:13:56 -04:00
cf0f7c0448
broad thrust of the mtp implementation
2025-08-13 02:21:17 -04:00
ee3a9fcf88
context : fix index overflow on huge outputs ( #15080 )
...
* context : fix overflow when re-ordering huge outputs
* context : fix logits size overflow for huge batches
2025-08-05 11:27:45 +02:00
a4569c41fd
llama : enable LLAMA_SET_ROWS=1 by default ( #14959 )
...
ggml-ci
2025-08-02 17:14:21 +03:00
ba42794c9e
graph : fix equal_seq() check ( #14986 )
...
ggml-ci
2025-08-01 06:38:12 +03:00
ca0ef2dddb
llama : clarify comment about pp and tg graphs [no ci] ( #14895 )
...
* llama : clarify comment about pp and tg graphs [no ci]
This commit clarifies the comment in `llama-context.cpp` regarding the
prefill prompt (pp), and token generation (tg) graphs.
The motivation for this is that I've struggled to remember these and had
to look them up more than once, so I thought it would be helpful to add
a comment that makes it clear what these stand for.
* squash! llama : clarify comment about pp and tg graphs [no ci]
Change "pp" to "prompt processing".
2025-07-27 12:10:51 +02:00
c1dbea752a
context : restore preemptive sched reset when LLAMA_SET_ROWS=0 ( #14870 )
...
ggml-ci
2025-07-25 14:28:06 +03:00
e4868d16d2
context : perform output reorder lazily upon access after sync ( #14853 )
...
* context : perform output reorder after lazily upon access after sync
ggml-ci
* cont : add TODO
2025-07-24 16:31:48 +03:00
d498af3d5a
graph : avoid huge warm-up graphs for MoE models ( #14753 )
...
* graph : avoid huge warm-up graphs for MoE models
ggml-ci
* cont : bump max nodes to 8x model tensors
2025-07-18 14:31:15 +03:00
8f974bc1e9
graph : refactor context to not pass gf explicitly ( #14629 )
...
ggml-ci
2025-07-18 08:29:28 +03:00
01612b7409
llama : reuse compute graphs ( #14482 )
...
* llama : reuse compute graphs
ggml-ci
* llama-bench : add graph reuse parameter
ggml-ci
* cont : remove the parameter and the sched resets
ggml-ci
* graph : rename update() to can_reuse()
ggml-ci
* params : remove is_same()
ggml-ci
* graph : set res->params in llm_graph_context constructor
ggml-ci
* graph : avoid set_max_nodes in llm_graph_result
ggml-ci
* kv-cache : reuse llama_context's graph result instance
ggml-ci
* context : reset the previous graph result upon memory updates
ggml-ci
* batch : llama_ubatch now carries its data instead of pointing to balloc
ggml-ci
* merge : fix build
ggml-ci
* graph : fix can_reuse() checks when flash-attention is disabled
* graph : move llm_graph_result impl in source file + debug env
ggml-ci
2025-07-17 19:08:33 +03:00
225e7a1438
llama : add high-throughput mode ( #14363 )
...
* kv-cache : prepare K/V buffers for separation
ggml-ci
* batched-bench : fix oob write
ggml-ci
* llama : add "virtual sequences"
ggml-ci
* llama : use "stream" vs "virtual sequence"
ggml-ci
* graph : fix stream splitting when KV cache is not used
ggml-ci
* kv-cache : add multi-stream save/load support
ggml-ci
* llama : add "--attn-streams" flag
ggml-ci
* kv-cache : fix handling when find_slot fails
ggml-ci
* kv-cache : restore find_slot impl
ggml-ci
* kv-cache : add comments
* kv-cache : add bounds checks for sequence id
ggml-ci
* cont : add n_seq_max to batch allocr
ggml-ci
* kv-cache : perform stream copies lazily after llama_synchronize
ggml-ci
* kv-cache : avoid throwing exceptions across the C boundary
ggml-ci
* CUDA: 4D FlashAttention support (#14628 )
* CUDA: 4D FlashAttention support
* CUDA: fix WMMA FA kernel
* llama : rename attn_streams -> kv_unified
ggml-ci
* common : rename kv_split -> kv_unified
ggml-ci
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2025-07-16 16:35:42 +03:00
9c9e4fc635
llama-context: add ability to get logits ( #14672 )
2025-07-14 21:01:41 +08:00
7b50d589a8
kv-cells : fix tracking of seq_pos ( #14339 )
...
* kv-cells : fix tracking of seq_pos during cache reuse
ggml-ci
* cont : improve error message
ggml-ci
* cont : add more comments
2025-06-23 12:27:35 +03:00
692e3cdd0a
memory : rename interface to llama_memory_context_i ( #14296 )
...
* memory : rename interface to llama_memory_context_i
ggml-ci
* cont : fix comments
* cont : use "mctx" for referencing a memory context
ggml-ci
2025-06-21 08:03:46 +03:00
4c9fdfbe15
ubatch : new splitting logic ( #14217 )
...
ggml-ci
2025-06-20 10:14:14 +03:00
d3e64b9f49
llama : rework embeddings logic ( #14208 )
...
* llama : rework embeddings logic
ggml-ci
* cont : fix rerank
ggml-ci
* cont : engrish [no ci]
* cont : fix rerank
ggml-ci
* server : support both embeddings and completions with single model
ggml-ci
* cont : avoid embeddings_org
ggml-ci
2025-06-16 14:14:00 +03:00
c311ac664d
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ ( #14188 )
...
ggml-ci
2025-06-15 10:08:58 +03:00
b9912ac570
batch : auto-gen positions + verify multi-sequence input ( #14177 )
...
* batch : verify multi-sequence input batches
ggml-ci
* cont : auto-gen positions + verify multi-seq input
ggml-ci
* cont : first print debug info, then perform validation
ggml-ci
* cont : fix position auto-gen + add comments
ggml-ci
2025-06-15 09:18:37 +03:00
60c666347b
batch : rework llama_batch_allocr ( #14153 )
...
* batch : rework llama_batch_allocr
ggml-ci
* cont : move validation inside class
ggml-ci
* cont : move output counting to class
ggml-ci
* cont : minor
ggml-ci
* batch : add TODOs
ggml-ci
2025-06-13 13:47:55 +03:00
f6e1a7aa87
context : simplify output counting logic during decode ( #14142 )
...
* batch : remove logits_all flag
ggml-ci
* context : simplify output counting logic during decode
ggml-ci
* cont : fix comments
2025-06-12 11:50:01 +03:00
c3ee46fab4
batch : remove logits_all flag ( #14141 )
...
ggml-ci
2025-06-12 11:49:26 +03:00
9596506965
kv-cache : fix split_equal handling in unified implementation ( #14130 )
...
ggml-ci
2025-06-12 10:02:15 +03:00
a20b2b05bc
context : round n_tokens to next multiple of n_seqs when reserving ( #14140 )
...
This fixes RWKV inference which otherwise failed
when the worst case ubatch.n_seq_tokens rounded to 0.
2025-06-12 02:56:04 -04:00
745aa5319b
llama : deprecate llama_kv_self_ API ( #14030 )
...
* llama : deprecate llama_kv_self_ API
ggml-ci
* llama : allow llama_memory_(nullptr)
ggml-ci
* memory : add flag for optional data clear in llama_memory_clear
ggml-ci
2025-06-06 14:11:15 +03:00
487a5e0401
context : fix SWA-related warning for multiple sequences ( #14045 )
2025-06-06 13:29:18 +03:00
d17a809ef0
llama : support multiple classifier outputs and labels ( #13940 )
2025-06-06 09:03:25 +02:00
7f37b6cf1e
memory : migrate from llama_kv_cache to more generic llama_memory ( #14006 )
...
* memory : merge llama_kv_cache into llama_memory + new `llama_memory` API
ggml-ci
* context : fix casts
ggml-ci
2025-06-05 15:29:22 +03:00
9e31bec4fd
context : fix pos_min initialization upon error decode ( #14008 )
...
ggml-ci
2025-06-05 09:06:29 +03:00
3e63a58ef7
kv-cache : refactor the update/defrag mechanism ( #13988 )
...
* kv-cache : refactor update mechanism
ggml-ci
* memory : improve status handling
* defrag : reset head + add comments
ggml-ci
* cont : minor fixes
ggml-ci
2025-06-04 18:58:20 +03:00
803f8baf4f
llama : deprecate explicit kv_self defrag/update calls ( #13921 )
...
ggml-ci
2025-05-31 15:58:33 +03:00
3600cc2886
llama : use n_swa + n_ubatch cells for SWA cache ( #13833 )
...
* llama : use n_swa + n_ubatch cells for SWA cache
ggml-ci
* llama : add warning about multi-sqeuence SWA contexts
2025-05-31 15:57:44 +03:00
3f55f781f1
llama : auto-batch preparation ( #13845 )
...
* llama : auto-batch
ggml-ci
* context : simplify if branching
2025-05-31 12:55:57 +03:00
12d0188c0d
kv-cache : refactor + add llama_memory_state_i ( #13746 )
...
* kv-cache : simplify the "struct llama_kv_cache" interface
ggml-ci
* kv-cache : revert the (n_swa + n_ubatch) change (for next PR)
ggml-ci
* kv-cache : some comments
ggml-ci
* context : fix graph reserve for multiple sequences
ggml-ci
* kv-cache : fix typo [no ci]
* kv-cache : fix find_slot() logic for free slots
ggml-ci
* llama : add TODO for deprecating the defrag API in the future
* kv-cache : improve find_slot() using min/max seq pos info
ggml-ci
* llama : handle aborts and compute errors
ggml-ci
* memory : extract state into llama_memory_state
ggml-ci
* kv-cache : add comments
ggml-ci
* server : update batching logic to reset n_batch on successful decode
* server : upon full re-processing, remove the sequence from the cache
* kv-cache : add TODO for doing split_equal when split_simple fails
ggml-ci
2025-05-31 10:24:04 +03:00
4f81b33e32
llama : validate seq id batch input ( #13809 )
...
* llama : validate seq id batch input
ggml-ci
* cont : fix the fix
ggml-ci
2025-05-27 09:40:59 +03:00
79c137f776
examples : allow extracting embeddings from decoder contexts ( #13797 )
...
ggml-ci
2025-05-26 14:03:54 +03:00
de2ef53a4b
kv-cache : rework kv_cell ( #13706 )
...
* kv-cache : rework kv_cell
ggml-ci
* kv-cells : use "shift" instead of "delta" consistently
ggml-ci
* llama : add llama_max_parallel_sequences()
ggml-ci
* kv-cells : update comments [no ci]
* context : fail upon construction if sequences exceed max value
ggml-ci
* kv-cells : get_pos() -> pos_get() + comments
ggml-ci
* kv-cells : fix tracking of "used" cells
ggml-ci
2025-05-25 16:34:36 +03:00
samuel
Aaron Lee
compilade
Georgi Gerganov
Daniel Bevenius
Aman Gupta
Sigbjørn Skjæret