Georgi Gerganov 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

..

batched

common : refactor downloading system, handle mmproj with -hf option (#12694)

2025-04-01 23:44:05 +02:00

batched.swift

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

convert-llama2c-to-ggml

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

deprecation-warning

Update deprecation-warning.cpp (#10619)

2024-12-04 23:19:20 +01:00

diffusion

Support diffusion models: Add Dream 7B (#14644)

2025-07-16 20:03:51 +08:00

embedding

llama : add high-throughput mode (#14363)

2025-07-16 16:35:42 +03:00

eval-callback

eval-callback : check for empty input (#14539)

2025-07-05 07:18:09 +03:00

gen-docs

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

gguf

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

gguf-hash

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

gritlm

llama : rework embeddings logic (#14208)

2025-06-16 14:14:00 +03:00

jeopardy

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

llama.android

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

llama.swiftui

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

lookahead

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

lookup

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

parallel

llama : add high-throughput mode (#14363)

2025-07-16 16:35:42 +03:00

passkey

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

retrieval

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

save-load-state

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

simple

fix: check model pointer validity before use (#13631)

2025-05-19 13:25:41 +03:00

simple-chat

simple-chat : fix context-exceeded condition (#14494)

2025-07-02 14:12:07 +03:00

simple-cmake-pkg

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

speculative

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

speculative-simple

llama : deprecate llama_kv_self_ API (#14030)

2025-06-06 14:11:15 +03:00

sycl

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

training

examples/training: Fix file name in README (#13803)

2025-05-26 16:55:24 +02:00

chat-13B.bat

…

chat-13B.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

chat-persistent.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

chat-vicuna.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

chat.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

CMakeLists.txt

Support diffusion models: Add Dream 7B (#14644)

2025-07-16 20:03:51 +08:00

convert_legacy_llama.py

metadata: Detailed Dataset Authorship Metadata (#8875)

2024-11-13 21:10:38 +11:00

json_schema_pydantic_example.py

py : type-check all Python scripts with Pyright (#8341)

2024-07-07 15:04:39 -04:00

json_schema_to_grammar.py

grammar : handle maxItems == 0 in JSON schema (#13117)

2025-04-26 10:10:20 +02:00

llama.vim

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

llm.vim

llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)

2023-08-30 09:50:55 +03:00

Miku.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

pydantic_models_to_grammar_examples.py

llama : move end-user examples to tools directory (#13249)

2025-05-02 20:27:13 +02:00

pydantic_models_to_grammar.py

pydantic : replace uses of __annotations__ with get_type_hints (#8474)

2024-07-14 19:51:21 -04:00

reason-act.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

regex_to_grammar.py

py : switch to snake_case (#8305)

2024-07-05 07:53:33 +03:00

server_embd.py

llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)

2025-04-08 19:54:51 +03:00

server-llama2-13B.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

ts-type-to-grammar.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00