* Disable K Hadamard transform if K-head size is not a power of 2
* Allow Hadamard transform for head sizes that are not power of 2
* Give more details why Hadamard is not possible
* Arghh
* ggml: ggml_dequant_hadamard fused op for MLA -khad path
Adds a new ggml op that fuses (ggml_cast -> F32) + (ggml_hadamard) into a
single kernel. Reads a quantized (or F16/F32) source and produces a per-
Hadamard-block F32 chunk with the inverse transform applied, without
materializing a full-size F32 intermediate buffer.
Motivation: the MLA pp_opt path in build_deepseek2.cpp un-encodes the
H-applied cache_nope view at every PP call. Today that runs as a cast
(quant -> F32) followed by a separate ggml_hadamard kernel, costing two
full-size F32 passes per layer per rank per call. Fusing them halves
the bandwidth on the un-encode and removes one kernel launch.
CUDA kernels in dequant_hadamard.cu lift the Walsh-Hadamard butterfly
from hadamard.cu and dequant helpers from dequantize.cuh:
* qr=1 layout (q8_0): consecutive dequant pair, stage 1 fused with load
* qr=2 layout (q4_0 / q4_1 / q5_0 / q5_1 / q6_0 / iq4_nl): dequant pair
at stride qk/2, explicit stage 1 after sync
* F16 has a dedicated kernel
* F32 source falls back to the standalone Hadamard op
CPU impl in iqk_cpu_ops.cpp composes the existing type_traits.to_float
dequant with fast_ht for graph completeness. nh in {64, 128, 256, 512}.
* MLA-TP: Hadamard pretransform of wv_b/wk_b_pp for -khad
Fold the 64-block orthonormal Hadamard into wv_b and wk_b_pp once at
context init so the pp_opt mul_mats consume the K cache in its on-disk
encoded basis. The per-PP-call cache_nope un-Hadamard is then skipped
(rope half still un-applied — it goes to FA via concat, no wk_b multiply).
Math is identity by H^T H = I: mul_mat(H@wv_b, H@cache) = wv_b^T @ cache.
For mla=2/3 absorb, composes correctly with the existing post-FA
ggml_hadamard(kqv_compressed, 64).
All-or-nothing across layers under a castable type-allowlist (excludes
1-3 bpw IQ types whose requant blows up beyond PPL noise). Models with
ineligible weights fall back to the runtime un-Hadamard path unchanged.
Composes with the fused ggml_dequant_hadamard op (prior commit): with the
fold active only the rope half still runs the runtime transform, via the
fused kernel.
* MLA-TP: fix TG with -khad after wv_b/wk_b_pp fold
The absorb branch of build_deepseek2_tp_attention applies
ggml_hadamard to kqv_compressed after FA, then multiplies by
wv_b. Pre-fold this was needed because wv_b was un-encoded; with
the wv_b fold (prior commit) the mul_mat already expects
H-encoded kqv_compressed:
mul_mat(H @ wv_b, kqv_encoded) = wv_b^T @ H @ H @ kqv_unencoded
= wv_b^T @ kqv_unencoded (H @ H = I)
Skip the post-FA hadamard when model.khad_pretransformed is set
so the two H applications cancel instead of double-applying.
Affects the absorb branch: TG (n_tokens=1), short-context PP
(n_kv < 1024), and models without wk_b_pp. Long-context PP goes
through the pp_opt branch and is unrelated/unchanged.
Reported by @ikawrakow on PR 1852. Verified across mla={1,2,3} x
khad={on,off} x -ctk={q8_0,q4_0} on GLM-4.7-Flash IQ5_K and the
unsloth IQ4_XS variant ik used to reproduce.
* ggml_hadamard: accept F16 and quant sources; drop GGML_OP_DEQUANT_HADAMARD
Per @ikawrakow review on PR 1852: subsume the per-source-type dispatch
into the existing GGML_OP_HADAMARD instead of carrying a separate enum
entry, op constructor, and standalone files.
ggml_hadamard's API is unchanged from the call-site perspective. The
constructor's F32-only assertion is dropped; ggml_cuda_op_hadamard and
iqk_hadamard now dispatch internally:
- F32 source: existing F32 butterfly (unchanged)
- F16 source: dedicated kernel
- q8_0 / q4_0 / q4_1 / q5_0 / q5_1 / q6_0 / iq4_nl: fused dequant +
butterfly kernel (lifted from the deleted dequant_hadamard.cu)
- CPU side composes traits.to_float with fast_ht
Net diff: -80 lines. Removes dequant_hadamard.{cu,cuh}, the enum entry,
op table rows, ggml_dequant_hadamard constructor, dispatch cases, and
the DEQUANT_HADAMARD supports_op block.
Verified clean build + TG smoke (mla=3 +khad q8 on GLM-4.7-Flash-IQ4_XS,
same coherent output as prior commit on feat/dequant-hadamard).
* MLA TP prompt processing optimisation
Adds a per-rank prompt-processing path to build_deepseek2_tp_attention
that materialises K/V from the compressed latent cache and runs a
standard flash_attn instead of the FlashMLA-3 absorb kernel the TP
attention currently uses for all batch sizes. Affects MLA archs under
-sm graph (DEEPSEEK2, GLM_DSA, MISTRAL4).
Gated on n_tokens >= 128 (set by caller) AND n_kv >= 1024. Below
either threshold the absorb path runs unchanged. Token generation
takes the absorb path; only prompt processing at non-trivial context
materialises.
A second piece pre-computes wk_b in a pp_opt-favouring orientation
(wk_b_pp: [kv_lora_rank, qk_nope, n_head]) at llm_prepare_mla time,
so the per-PP-call materialise can mul_mat against the latent cache
directly without an F16 cast + permute + ggml_cont on wk_b each call.
Path A (wkv_b in GGUF) and Path B (only wk_b/wv_b in GGUF) both
populate wk_b_pp through the standard per-rank replica setup.
Measured on 8x RTX 3090, -sm graph -mla 2 -fa on:
DSV2.5 IQ2_XS c=8k ub=2048 PP +51% to +60%
GLM-4.7-Flash IQ4_XS c=32k ub=2048 PP -6% (PP@0) to +77% (PP@30720)
GLM-5.1 IQ1_S q4_0 c=16k ub=2048 PP +5% to +9%
PPL parity within +/-0.2 noise (DSV2.5 bit-identical 5.3917, GLM-4.7
8.83 vs 8.96, GLM-5.1 6.96 vs 7.00). Token-generation throughput
unchanged within noise.
Compute buffer at init:
DSV2.5 -54 MiB total (allocator noise)
GLM-4.7-Flash +1042 MiB total (~+173 MiB per non-output device)
GLM-5.1 0 (MoE intermediates dominate)
* MLA TP: respect mla=1 vs mla=3 distinction, rename attn_k_b_pp -> attn_kv_b
ikawrakow/ik_llama.cpp#1841 review feedback: the pp_opt path lost the
intended trade-off where mla=1 forgoes pp_opt to save VRAM and mla=3 pays
the wk_b_pp tensor cost for faster long-context PP.
- llm_prepare_mla second pass: gate wk_b_pp synthesis on mla > 1.
Models that ship wk_b in their GGUF (mainline format) no longer
allocate the pp_opt-favoring K weight under mla=1.
- llm_prepare_mla first pass (wk_b synthesis from wkv_b): keep
unconditional under -sm graph. The wk_b_pp materialization here
shares the wk_b_f32 intermediate with the wk_b synthesis above, and
isolating just the wk_b_pp branch leaves the synthesized wk_b in a
state that makes the absorb path produce inf on some quant combos
(DSV2.5 IQ2_XS). Trade: the synthesized-wkv_b path still pays the
wk_b_pp allocation under mla=1, but the bigger compute-buffer
saving (no pp_opt branch at runtime) still applies.
- build_deepseek2 outer pp_opt: include cparams.mla_attn > 1 in the
pp_opt definition itself, so mla=1 is bypassed throughout (TP and
non-TP attention paths).
- build_deepseek2 tp pp_opt: require wk_b_pp present. Drop the dead
runtime wk_b transpose fallback (unreachable now that wk_b_pp is
guaranteed when tp_pp_opt fires).
- llama_kv_cache_init: have_wkv_b probe now treats wk_b_pp (attn_kv_b)
as equivalent to wkv_b for the purposes of allowing mla>1 to stay
put. Without this, -sm graph models that have wk_b/wv_b separately
in the GGUF (no combined wkv_b) would silently downgrade to mla=1.
- Rename the synthesized tensor "attn_k_b_pp.weight" -> "attn_kv_b.weight"
to match the mainline naming ik uses.
GLM-5.1 in particular benefits: its mla=3 PP improvement over mla=1 is
negligible on this arch (~0.4% in our sweeps), so users save the
runtime cost by sticking to mla=1.
* MLA tensor parallelism under -sm graph (DEEPSEEK2/GLM_DSA/MISTRAL4)
Extends -sm graph (split-mode graph) to MLA-style attention across the
DEEPSEEK2, GLM_DSA, and MISTRAL4 architectures. Previously these archs
fell back to -sm layer regardless of the user's flag.
Implementation:
- Per-rank attention build in build_deepseek2_tp_attention with
view-sliced FlashAttention, split-buffer output projection, and
ggml_reduce across devices
- wk_b / wv_b absorbed weights replicated per device via materialize()
in llm_prepare_mla (these can't live in a split buffer)
- KV cache replication path (replicated_k_l) for graph-mode TP
- distribute_mla_tensors_for_split_mode_graph routes attention/norm
tensors into ctx_split; expert tensors stay per-layer
- Implements ggml_backend_cuda_split_buffer_get_tensor for the
replicated / row-split / col-split inverse paths
- Early-reject guard in src/llama.cpp that auto-downgrades -sm graph
to -sm layer (with a warning) when incompatible loader flags are set:
-ncmoe, -cmoe, -ot, -rtr, -muge
New CLI flag:
- -gap | --graph-attn-precision <f16|f32> (default f16)
See the PR description for the full validation matrix (3 archs x 2/4/8
GPU counts), perf numbers, VRAM accounting, and known limitations.
* Some tweaks
* materialize lambda: per-head split for graph-mode tp_replicate
7dd19e19 changed wk_b/wv_b distribution from mirror to per-head split
(split_dim=2) via prepare_split_tensors. That path only fires when
wk_b/wv_b are loaded from GGUF.
Models that store only wkv_b in GGUF derive wk_b/wv_b at load via
llm_prepare_mla, going through the materialize lambda, which was
untouched and still produced mirror replicas (split_dim=-1, full n_head
per device).
build_deepseek2_tp_attention now does mul_mat(wk_b_local, q_nope_perm)
without the prior view_3d slice, so a mirror replica passes an n_head
tensor where the kernel expects n_head_local. Result: silent SIGSEGV
right after model load.
Mirror logic in materialize is replaced with the same per-head split as
prepare_split_tensors: head_offsets derived from wo split, each rank
gets a tensor with ne[2]=n_head_local, data copied from the appropriate
source byte slice. Singular `computed` tensor keeps full metadata for
tensors_by_name lookups.
Tested: 8x3090, -sm graph -mla 3 -fa on now boots cleanly and
sweep-benches without crash. Log confirms new path: "Computed
blk.X.attn_k_b.weight ... split across N devices on dim=2".
* cleanup: indent fix + remove dead view_3d slicing and debug printf
- build_deepseek2.cpp: re-indent the self_attention block in
build_deepseek2_layer_attention (lines 253-670). Block was at column 0
inside a function body; now at the expected 4/8-space indent.
- build_deepseek2.cpp: drop the commented-out view_3d slicing and debug
printfs left over after 7dd19e19's switch to direct mul_mat on
per-rank wk_b_local / wv_b_local. Update the stale 'wk_b is
replicated (split_dim=-1)' comment to match the new split_dim=2
reality.
- ggml-cuda.cu: remove the leftover debug printf in
ggml_backend_cuda_split_buffer_get_tensor.
No behavior change. Verified with a clean rebuild and DSV2.5 +
GLM-4.7-Flash sweep-bench runs.
* llm_load_tensors: gate incompatible-flag warning to MLA archs
The -ncmoe / -rtr / -muge / -ot warning under -sm graph currently fires
for all archs that support graph mode. That's an over-reach: the
incompatibility is specific to the MLA TP paths (DEEPSEEK2, GLM_DSA,
MISTRAL4) — Gemma4 graph mode existed pre-PR and works with those flags.
Gate the warning to MLA archs only.
Also refreshes two stale comments left over from the wk_b/wv_b
mirror -> per-head-split rewrite:
- src/llama.cpp llm_prepare_mla: "Replicate wk_b/wv_b ..." now reads
"Per-head split wk_b/wv_b ..." to match what the materialize lambda
actually does post-823a39e2.
- src/llama-load-tensors.cpp distribute_mla_tensors_for_split_mode_graph:
drop the wkv_b row-split mention (wkv_b is no longer created under
graph mode after 7dd19e19) and correct the wk_b/wv_b distribution
description (per-head split, not per-device replicated).
---------
Co-authored-by: Kawrakow <iwankawrakow@gmail.com>
* Use build_std_attention for Gemma4 when possible
It is possible for the 26b MoE and 31b dense models.
It is not possible for the E4B/E2B vaiants because they
don't have KV cache in each layer.
* Standardize Gemma4 dense ffn
* WIP: Gemma4 split mode graph
Runs but produces NaNs
* WIP: Gemma4 split mode graph
Runs but very high PPL. At least it is no longer NaN.
* WIP
* This works!
* Put attn_norm, attn_post_norm, ffn_norm, ffn_post_norm on all GPUs
* Fix crash when saving/loading KV cache
* WIP: split mode graph for Gemma4-MoE - crashes
* Split mode graph for Gemma4-MoE - this works
* Disable SWA optimization
Something goes wrong there
* Consolidate MoE and dense graph parallel
* Use build_std_attention for Gemma4 when possible
It is possible for the 26b MoE and 31b dense models.
It is not possible for the E4B/E2B vaiants because they
don't have KV cache in each layer.
* Standardize Gemma4 dense ffn
* WIP: Gemma4 split mode graph
Runs but produces NaNs
* WIP: Gemma4 split mode graph
Runs but very high PPL. At least it is no longer NaN.
* WIP
* This works!
* Put attn_norm, attn_post_norm, ffn_norm, ffn_post_norm on all GPUs
* Fix crash when saving/loading KV cache
* Gemma4: WIP
* Gemma4: WIP - runs with totally wrong results
* Gemma4: WIP - add CPU 512, 512 FA
* Gemma4: WIP
It gives a meaningful response in llama-cli, but PPL is still much too
high. Is this due to tokenizer issues?
* Gemma4: this works
I had forgotten the softcap on the final output.
* Remove log
* Gemma4: WIP E4B/E2B
* Gemma4: Q4B/E2B appear to work now
* gemma4: tokenizer fixes
* WIP: support pre-merged up/gate experts
Haha, mainline has elected to arrange the merged tensors
the other way around compared to what I had done in the on-the-fly merge.
* Change the order of on-the-fly packed up/gate
* OpenAI
* CUDA TG
* CPU
* Split mode graph for models with pre-merged ffn_up/ffn_gate experts
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
Loads and starts running, crashes with illegal memory access in
quantize_mmq_q8_1. This almost always indicates NaNs in the input
to the MoE FFN part.
* WIP
* WIP
Loads and runs, wrong results (very high PPL)
Performance looks promising, around 25% better than previous sm graph.
Needs f32 or bf16 graph reduce type.
* WIP - still wrong
* Fix after rebase
* WIP
* WIP
* This seems to be working for dense Qwen3.5!!!
* WIP: Qwen3-Next is not quite working
* Some cleanup
* Disable Qwen3-Next for now
* Disable graph parallel when mmproj was specified
* Read/write split recurrent state
* That should not crash
* Re-enable vision - it works now
* Recurrent layers should now be counted for split cache
* wip: port MTP architecture
Ports the Multi-Token Prediction (MTP) architecture to the older `llama.cpp` codebase used by `ikllama`.
Changes include:
- Updating `llama_batch` to support `mtp_params`.
- Modifying `llama_decode_internal` (and `encode`) to handle MTP operations (Warmup, Update, Draft).
- Adding public APIs for MTP state management (`llama_set_draft_input_hidden_state`).
- Adapting the embedding extraction logic to skip MTP update passes.
* Refactors `server_slot` to support generic speculative decoding (MTP or Draft Model).
* core: enable hybrid outputs (logits + embeddings) for MTP support
* fix(mtp): correct KV-cache slot finding for updates
* fix(mtp): persist hidden states to prevent context corruption during drafting
* refactor(mtp): clean unused code
* fix(mtp): update server to new functions name
* fix(mtp): fix graph and save hidden state
* mtp: refactor integration, context params and kv cache search
* mtp: fix hidden state extraction and speculative acceptance flow
* server: fix MTP warmup for long prompts and reset token buffer
* llama: refactor MTP operation state to context parameters
* server: fix n_past calculation in MTP acceptance
* llama: fix mtp enable flags
* speculative: refactor MTP to use common_speculative interface
* context: remove unused signatures
* clip: fix deprecated enum-enum conversion warning
* common: fix format string crash in help message
* context: fix mtp activation logic
* Optimizing q3next TG
* Fused add -> softplus -> mul on CUDA
* Remove forgotten debug log
* Increase ggml context size
Required for Qwen3-Next with batch/u-batch size of 4096
* WIP
* Avoid some contiguous ops
* Avoid some repeats
* Avoid some more repeats
* qwen3next: add architecture support and recurrent-state fixes
* qwen3next: optimize broadcast sub and single-seq ssm conv
* cuda: build MoE row mapping on device in mul_mat_id
* cuda: add guarded multi-seq fast path for ssm_conv
* docs: update qwen3next perf report for cuda MoE/SSM tuning
* cuda: reduce qwen3next moe/ssm sync overhead and refresh eval
* qwen3next: split cpu/cuda eval builds and tune PP scheduling
* qwen3next: harden seq-state flow and support optional dense FFN layers
* qwen3next: trim delta-net graph overhead in chunking path
* qwen3next: remove redundant v_conv cont in delta path
* qwen3next: avoid extra cont on linear attention output
* qwen3next: drop redundant cont before recurrent state flatten
* qwen3next: keep recurrent state in 4d layout through delta path
* qwen3next: add fused delta-net op and wire model path
* tests: add backend-op coverage for ggml_delta_net
* qwen3next: add runtime switch for fused delta-net path
* docs: refresh qwen3next perf review and benchmark matrix
* qwen3next: default fused delta-net off and document quality checks
* qwen3next: add decode-only fused delta mode
* qwen3next: make fused delta safe by default and fix fused tensor layout
* qwen3next: warn when forcing fused decode mode
* qwen3next: add fused-delta regression runner script
* qwen3next: integrate fused regression into eval harness
* qwen3next: clean up chunked delta-net shape handling
* qwen3next: add absolute sanity guards to fused regression
* qwen3next: add unified regression runner script
* qwen3next: disable flash-attn for cpu-only contexts
* docs: reconcile qwen3next status and remaining upstream gaps
* common: add qwen3next fused-delta runtime flag
* cuda: add qwen3next delta-net kernel dispatch override
* docs: update qwen3next quality and serving baseline findings
* qwen3next: keep fused delta on safe path and remove PR artifacts
* qwen3next: align autoregressive delta-net decode layout
* Revert "qwen3next: align autoregressive delta-net decode layout"
This reverts commit 9241164a5ea9e032a2456fbf2dd0bf798b264fd7.
* cuda: port solve-tri fast-paths for qwen3next delta-net
* qwen3next: add fused-delta runtime flag and drop env toggle
* qwen3next: make fused delta single-flag and default on
* Account for GPU arch differences
* Revert "cuda: build MoE row mapping on device in mul_mat_id"
This reverts commit 89e9ecfa840b04e88699ab3803eb732cd78727f9.
* qwen3next: drop non-essential MoE scheduling and split heuristics
* qwen3next: avoid generic ggml_sub broadcast changes
* llama: restore only_active_experts log message
* Remove unnecessary hacks, disable fusion for now.
* qwen3next: port hybrid recurrent state memory semantics
* qwen3next: clean up recurrent state slot plumbing
* qwen3next: fix hybrid V-cache layout plumbing
* qwen3next: guard recurrent state slots against kv capacity
* qwen3next: persist recurrent state in session data
- serialize/restore qwen3next cache.s_l in state/session paths\n- bump session and sequence-state file versions for format change\n- fallback to single-token chunking for mixed repeated seq_id batches
* qwen3next: drop unused fused-delta builder path
- remove dead build_delta_net_fused lambda\n- remove unused llm_build_context::fused_delta member
* qwen3next: remove unused fused-delta CLI/context plumbing
- drop -fd/-no-fd options and related YAML dump field\n- remove fused_delta fields from public/internal context params\n- remove fused_delta assignment and logging in context init
* ggml: remove unused DELTA_NET operator stack
* Missing include
* Reorder ops/unary ops
So we don't change again the enum values of the mul mat ops
* Minor
* Discard unnecessary changes in llama-build-context.cpp
* Minor
* Revert "Discard unnecessary changes in llama-build-context.cpp"
This reverts commit edadb80ed68c4c0831e9c22609a9a3af19be9735.
* Increase GGML_SCHED_MAX_SPLITS - required for larger u-batches
* Fix CPU concat in the TG case: 7.25 -> 10.5 t/s for Qwen3Next
* Fix CPU sum_rows: 10.5 -> 13.6 t/s for Qwen3Next
It was single-threaded and was taking ~25% of the computation time
during TG. It is now down to 2%.
Strangely enough, I measure 13.6 t/s with llama-bench, but if I
let the model give me an actual response with llama-cli, I get close
to 17 t/s.
* Fix CPU scale: 13.6 -> 16.7 t/s for Qwen3Next
For Qwen3Next there is a scale op on a largish tensor (548k elements)
that has a single row for TG, so was done in a single thread.
We now simply use blocks of 1024 elements.
* Optimize CPU mul: 16.7 -> 17.6 t/s for Qwen3Next
* CPU: fuse transpose -> cont -> sum_rows -> transpos: 17.6 -> 23.1 t/s for Qwen3Next
* Optimize CPU repeat: 176 -> 200 t/s for Qwen3Next PP-512
* Multithreading for OP_SUB
* Don't commit with timing trace on
* Multithread neg and sigmoid
* Be able to turn on/off fusion more easily (CPU)
* Name the mul_mat ops so we know where the time goes
* WIP
* Much better PP on CUDA
* CUDA: fuse transpose -> cont -> sum_rows -> transpose
Needs non-coontiguous variant of sum_rows.
On the CPU this gave 30+% improvement in TG performance,
on CUDA ist is disapointing 6-7%. I guess, this is because
Georgi's cont CPU implementation was so bad that skipping
it made such a big difference.
* CUDA: faster mul for special case relevant for Qwen3Next
Worth 1% in TG
* Fix CPU OP_CONT
---------
Co-authored-by: yurko <yurko@local>
Co-authored-by: Yurko <yurko@example.com>
Co-authored-by: yurko <yurko@pop-os.tail5a1a6b.ts.net>
Co-authored-by: Yurko Hoshko <YurkoHoshko@users.noreply.github.com>
* WIP
* This works but is slow
* Turn off the up / gate clamps for now
* OK we need the clamping
* Fuse the clamp (CUDA)
* Fuse the clamp (CPU)
* WIP
* Be able to use merged q, k, v
* Be able to use merged up/gate experts
* Fuse the clamp (CUDA mmvq)
* WIP: graph parallel for Step-3.5
* WIP
* This should be it
* Cleanup
* Fix merge
* WIP
* This works but is slow
* Turn off the up / gate clamps for now
* OK we need the clamping
* Fuse the clamp (CUDA)
* Fuse the clamp (CPU)
* WIP
* Be able to use merged q, k, v
* Be able to use merged up/gate experts
* Fuse the clamp (CUDA mmvq)
* WIP - not working
* WIP - not working
* WIP - GPT-OSS working
However, extremely stupid. The only way I could correctly repack the
up/gate experts is to copy up and gate into host buffers, repack
into another host buffer, copy back into the ffn_up_gate_exps tensor.
This is going to be very slow for giant 500 GB models.
My attempts to do this via a compute graph on the backend holding
the tensors was unsuccessful.
For GPT-OSS-20B I see ~6-7% better PP when using the original
ik_llama.cpp fused_up_gate CUDA implementation, and ~10% when
using the small batch size implementation.
Other models are not working yet on CUDA as I need to fix the
fused mul-unary implementation.
* WIP
* WIP - Qwen3-MoE (and hopefully all others) working
But when I say here and in the previous commit "working",
I mean PP is working. TG is still broken.
* WIP: TG seems to be working
* Minor
* Add command line option to merge experts up/gate
* Add merge up/gate command line parameter to llama-bench
* Turn off merge_up_gate_exps if split mode graph
It is not yet implemented
* When no bias, allow merging up/gate with tensor overrides
* Arghh, we need to increase the context size again
* Cleanup
* Mimo-2 support
* Fix bug for head sizes not being the same
It still does not solve the Mimo-2 quantized cache issue.
* Fix quantized cache
* Minor
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Remove most of split mode row
* WIP
* WIP: also allocate the KV cache using tensor split
* WIP: it runs with wrong result
But it also looks like the backend scheduler is not going to help:
* It copies mask and input positions to GPU 0
* => RoPE ops must run on GPU 0
* => To proceed attn evaluation, GPU 1 must wait for GPU 0 to finish its
entire attn calculation
* Same with FFN. The rms_norm gets scheduled on GPU 0. Hence, GPU 1 must
wait for GPU 0 to finish its entore FFN calculation before it can
start (as it needs to copy the result of rms_norm from GPU 0)
* => Seems useless without writing a bespoke TP scheduling
* WIP
* This works, but it is slow
* This is slightly better
the graph is still not being computed in parallel.
Why? Because the scheduler creates graph splits where the
result of the computation on one GPU becomes an input for the
other split. Hence, to trigger the computation on the second GPU
one needs to wait for the computation on the first GPU to finish,
even thiough the two can be done in parallel up to the sunchronization
point. So, all that is left to do is to trick the scheduler to create
to splits that can be done in parallel, and then have a graph split
where the results get combined.
* Playing games with the scheduler
This change tricks it into doing the right thing^TM.
Still quite a bit slower than split mode layer for the 8B LlaMA model.
But for the 70B LlaMA it now beats split mode layer for TG:
28 t/s vs 24.4 t/s. PP is 627 t/s vs 744 t/s.
In comparison, split mode "row" in mainline gets
484 t/s PP and 19.3 t/s TG.
* Fix attn split
Granularity for Wq, Wo is not just head size, but
head size * gqa_ratio.
Else the Wk, Wv tensors end up not being a multiple of the
head size when we divide the split determined by Wo with
the gqa_ratio.
* Show memory used per device
* Make it work with partial offload
but no tensor overrides yet, just ngl < num_layers.
* Allow for f16 source in fused_rms_norm
* This results in faster PP.
Now PP is faster than split mode layer for L3-70B.
* Rename split mode "row" to split mode "graph"
* Leave FFN partial results as f16
* WIP GLM4.5 - runs with wrong results
* WIP GLM4.5 - this works
PP is already better than split mode layer, but TG for zero context
is kind of low - 60 vs 92 t/s. TG becomes better than split mode layer
at around 20k tokens. PP at 26k tokens is 1.55X of sm layer.
* Work around compiler bug
It issues a warning that there is an extra semicolon outside of a function,
but there isn't. If I remove the anonymous namespace and turn the
functions inside into static, the warning disapears, so clearly
a compiler bug.
* Make graph reuse work with split mode graph
* Remove more split mode row remnants
* WIP tensor overrides
Runs with wrong results, don't see where the issue could be.
* This works but is slow
Still does not work for row-interleaved quants
* Slightly better
* Slightly better
* Row-interleaved quants work
* Better
* Minor
* Guarad against using split mode "graph" for unsupported models
* Guards against using merge_qkv with split mode "graph"
* WIP split mode attn
Works for LlaMA models, but not for GLM-4.5.
Doesn't seem to improve performance, so I guess no point in trying to
fix it.
* Split mode graph for qwen3moe
* Try to better distribute the splits
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* RPC support multiple devices
* rpc : update documentation (#16441)
Update the README file to match the newly added functionality of
exposing multiple devices from a single server.
Co-authored-by: Diego Devesa <slarengh@gmail.com>
# Conflicts:
# examples/rpc/README.md
* Remove memory settings
* rpc : cache and reuse compute graphs (#15405)
Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.
* Add -cpu to include cpu backend
---------
Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Radoslav Gerganov <rgerganov@gmail.com>
* Merge Q and K into a single tensor
* Make V mul mat follow QK mul mat
so they can be fused, which gives a slightly bbetter TG performance.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* llama_model and llama_hparams
* llama_build_context
Surprisingly small reduction in llama.cpp compile time given
the reduction in LOCs (22k -> 14k)
* LLM_TN
llama.cpp compilation: 50 s -> 33 s
* llama_quantize
* arch names
* All graph building is now in llm-build-context.cpp
* hparams loading
llama.cpp is now just 9300 LOC, but still takes 32 seconds to compile.
* We are now at 6 seconds to build the src folder
* load -> create
We are not actually loading the tensors, but just creating them.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
SamuelOliveirads
Kawrakow
David Young
Samuel Oliveira Alves
firecoperana
firecoperana
Thireus ☠